mrq/stable-diffusion-webui
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into PowerShell

Browse Source
This commit is contained in:
d8ahazard 2023-01-22 11:32:26 -06:00
commit 5929ece1f3
77 changed files with 3366 additions and 4104 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

663
LICENSE.txt Normal file
View File

@ -0,0 +1,663 @@
GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
Copyright (c) 2023 AUTOMATIC1111
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<https://www.gnu.org/licenses/>.

15
README.md
View File

@ -49,9 +49,9 @@ A browser interface based on Gradio library for Stable Diffusion.
- Running arbitrary python code from UI (must run with --allow-code to enable)
- Mouseover hints for most UI elements
- Possible to change defaults/mix/max/step values for UI elements via text config
- Random artist button
- Tiling support, a checkbox to create images that can be tiled like textures
- Progress bar and live image generation preview
- Can use a separate neural network to produce previews with almost none VRAM or compute requirement
- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image
- Styles, a way to save part of prompt and easily apply them via dropdown later
- Variations, a way to generate same image but with tiny differences
@ -76,13 +76,22 @@ A browser interface based on Gradio library for Stable Diffusion.
- hypernetworks and embeddings options
- Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
- Clip skip
- Use Hypernetworks
- Use VAEs
- Hypernetworks
- Loras (same as Hypernetworks but more pretty)
- A sparate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt.
- Can select to load a different VAE from settings screen
- Estimated completion time in progress bar
- API
- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML.
- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embeds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
- [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions
- [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
- Now without any bad letters!
- Load checkpoints in safetensors format
- Eased resolution restriction: generated image's domension must be a multiple of 8 rather than 64
- Now with a license!
- Reorder elements in the UI from settings screen
-
## Installation and Running
Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.

3041
artists.csv
View File

File diff suppressed because it is too large Load Diff

3
extensions-builtin/LDSR/ldsr_model_arch.py
View File

@ -1,7 +1,6 @@
import os
import gc
import time
import warnings
import numpy as np
import torch
@ -15,8 +14,6 @@ from ldm.models.diffusion.ddim import DDIMSampler
from ldm.util import instantiate_from_config, ismap
from modules import shared, sd_hijack
warnings.filterwarnings("ignore", category=UserWarning)
cached_ldsr_model: torch.nn.Module = None

20
extensions-builtin/Lora/extra_networks_lora.py Normal file
View File

@ -0,0 +1,20 @@
from modules import extra_networks
import lora
class ExtraNetworkLora(extra_networks.ExtraNetwork):
def __init__(self):
super().__init__('lora')
def activate(self, p, params_list):
names = []
multipliers = []
for params in params_list:
assert len(params.items) > 0
names.append(params.items[0])
multipliers.append(float(params.items[1]) if len(params.items) > 1 else 1.0)
lora.load_loras(names, multipliers)
def deactivate(self, p):
pass

199
extensions-builtin/Lora/lora.py Normal file
View File

@ -0,0 +1,199 @@
import glob
import os
import re
import torch
from modules import shared, devices, sd_models
re_digits = re.compile(r"\d+")
re_unet_down_blocks = re.compile(r"lora_unet_down_blocks_(\d+)_attentions_(\d+)_(.+)")
re_unet_mid_blocks = re.compile(r"lora_unet_mid_block_attentions_(\d+)_(.+)")
re_unet_up_blocks = re.compile(r"lora_unet_up_blocks_(\d+)_attentions_(\d+)_(.+)")
re_text_block = re.compile(r"lora_te_text_model_encoder_layers_(\d+)_(.+)")
def convert_diffusers_name_to_compvis(key):
def match(match_list, regex):
r = re.match(regex, key)
if not r:
return False
match_list.clear()
match_list.extend([int(x) if re.match(re_digits, x) else x for x in r.groups()])
return True
m = []
if match(m, re_unet_down_blocks):
return f"diffusion_model_input_blocks_{1 + m[0] * 3 + m[1]}_1_{m[2]}"
if match(m, re_unet_mid_blocks):
return f"diffusion_model_middle_block_1_{m[1]}"
if match(m, re_unet_up_blocks):
return f"diffusion_model_output_blocks_{m[0] * 3 + m[1]}_1_{m[2]}"
if match(m, re_text_block):
return f"transformer_text_model_encoder_layers_{m[0]}_{m[1]}"
return key
class LoraOnDisk:
def __init__(self, name, filename):
self.name = name
self.filename = filename
class LoraModule:
def __init__(self, name):
self.name = name
self.multiplier = 1.0
self.modules = {}
self.mtime = None
class LoraUpDownModule:
def __init__(self):
self.up = None
self.down = None
def assign_lora_names_to_compvis_modules(sd_model):
lora_layer_mapping = {}
for name, module in shared.sd_model.cond_stage_model.wrapped.named_modules():
lora_name = name.replace(".", "_")
lora_layer_mapping[lora_name] = module
module.lora_layer_name = lora_name
for name, module in shared.sd_model.model.named_modules():
lora_name = name.replace(".", "_")
lora_layer_mapping[lora_name] = module
module.lora_layer_name = lora_name
sd_model.lora_layer_mapping = lora_layer_mapping
def load_lora(name, filename):
lora = LoraModule(name)
lora.mtime = os.path.getmtime(filename)
sd = sd_models.read_state_dict(filename)
keys_failed_to_match = []
for key_diffusers, weight in sd.items():
fullkey = convert_diffusers_name_to_compvis(key_diffusers)
key, lora_key = fullkey.split(".", 1)
sd_module = shared.sd_model.lora_layer_mapping.get(key, None)
if sd_module is None:
keys_failed_to_match.append(key_diffusers)
continue
if type(sd_module) == torch.nn.Linear:
module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
elif type(sd_module) == torch.nn.Conv2d:
module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
else:
assert False, f'Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}'
with torch.no_grad():
module.weight.copy_(weight)
module.to(device=devices.device, dtype=devices.dtype)
lora_module = lora.modules.get(key, None)
if lora_module is None:
lora_module = LoraUpDownModule()
lora.modules[key] = lora_module
if lora_key == "lora_up.weight":
lora_module.up = module
elif lora_key == "lora_down.weight":
lora_module.down = module
else:
assert False, f'Bad Lora layer name: {key_diffusers} - must end in lora_up.weight or lora_down.weight'
if len(keys_failed_to_match) > 0:
print(f"Failed to match keys when loading Lora {filename}: {keys_failed_to_match}")
return lora
def load_loras(names, multipliers=None):
already_loaded = {}
for lora in loaded_loras:
if lora.name in names:
already_loaded[lora.name] = lora
loaded_loras.clear()
loras_on_disk = [available_loras.get(name, None) for name in names]
if any([x is None for x in loras_on_disk]):
list_available_loras()
loras_on_disk = [available_loras.get(name, None) for name in names]
for i, name in enumerate(names):
lora = already_loaded.get(name, None)
lora_on_disk = loras_on_disk[i]
if lora_on_disk is not None:
if lora is None or os.path.getmtime(lora_on_disk.filename) > lora.mtime:
lora = load_lora(name, lora_on_disk.filename)
if lora is None:
print(f"Couldn't find Lora with name {name}")
continue
lora.multiplier = multipliers[i] if multipliers else 1.0
loaded_loras.append(lora)
def lora_forward(module, input, res):
if len(loaded_loras) == 0:
return res
lora_layer_name = getattr(module, 'lora_layer_name', None)
for lora in loaded_loras:
module = lora.modules.get(lora_layer_name, None)
if module is not None:
res = res + module.up(module.down(input)) * lora.multiplier
return res
def lora_Linear_forward(self, input):
return lora_forward(self, input, torch.nn.Linear_forward_before_lora(self, input))
def lora_Conv2d_forward(self, input):
return lora_forward(self, input, torch.nn.Conv2d_forward_before_lora(self, input))
def list_available_loras():
available_loras.clear()
os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
candidates = \
glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.pt'), recursive=True) + \
glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.safetensors'), recursive=True) + \
glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.ckpt'), recursive=True)
for filename in sorted(candidates):
if os.path.isdir(filename):
continue
name = os.path.splitext(os.path.basename(filename))[0]
available_loras[name] = LoraOnDisk(name, filename)
available_loras = {}
loaded_loras = []
list_available_loras()

6
extensions-builtin/Lora/preload.py Normal file
View File

@ -0,0 +1,6 @@
import os
from modules import paths
def preload(parser):
parser.add_argument("--lora-dir", type=str, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))

30
extensions-builtin/Lora/scripts/lora_script.py Normal file
View File

@ -0,0 +1,30 @@
import torch
import lora
import extra_networks_lora
import ui_extra_networks_lora
from modules import script_callbacks, ui_extra_networks, extra_networks
def unload():
torch.nn.Linear.forward = torch.nn.Linear_forward_before_lora
torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_lora
def before_ui():
ui_extra_networks.register_page(ui_extra_networks_lora.ExtraNetworksPageLora())
extra_networks.register_extra_network(extra_networks_lora.ExtraNetworkLora())
if not hasattr(torch.nn, 'Linear_forward_before_lora'):
torch.nn.Linear_forward_before_lora = torch.nn.Linear.forward
if not hasattr(torch.nn, 'Conv2d_forward_before_lora'):
torch.nn.Conv2d_forward_before_lora = torch.nn.Conv2d.forward
torch.nn.Linear.forward = lora.lora_Linear_forward
torch.nn.Conv2d.forward = lora.lora_Conv2d_forward
script_callbacks.on_model_loaded(lora.assign_lora_names_to_compvis_modules)
script_callbacks.on_script_unloaded(unload)
script_callbacks.on_before_ui(before_ui)

36
extensions-builtin/Lora/ui_extra_networks_lora.py Normal file
View File

@ -0,0 +1,36 @@
import json
import os
import lora
from modules import shared, ui_extra_networks
class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
def __init__(self):
super().__init__('Lora')
def refresh(self):
lora.list_available_loras()
def list_items(self):
for name, lora_on_disk in lora.available_loras.items():
path, ext = os.path.splitext(lora_on_disk.filename)
previews = [path + ".png", path + ".preview.png"]
preview = None
for file in previews:
if os.path.isfile(file):
preview = "./file=" + file.replace('\\', '/') + "?mtime=" + str(os.path.getmtime(file))
break
yield {
"name": name,
"filename": path,
"preview": preview,
"prompt": json.dumps(f"<lora:{name}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
"local_preview": path + ".png",
}
def allowed_directories_for_previews(self):
return [shared.cmd_opts.lora_dir]

45
extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js
View File

@ -4,16 +4,10 @@
// Counts open and closed brackets (round, square, curly) in the prompt and negative prompt text boxes in the txt2img and img2img tabs.
// If there's a mismatch, the keyword counter turns red and if you hover on it, a tooltip tells you what's wrong.
function checkBrackets(evt) {
textArea = evt.target;
tabName = evt.target.parentElement.parentElement.id.split("_")[0];
counterElt = document.querySelector('gradio-app').shadowRoot.querySelector('#' + tabName + '_token_counter');
promptName = evt.target.parentElement.parentElement.id.includes('neg') ? ' negative' : '';
errorStringParen = '(' + tabName + promptName + ' prompt) - Different number of opening and closing parentheses detected.\n';
errorStringSquare = '[' + tabName + promptName + ' prompt] - Different number of opening and closing square brackets detected.\n';
errorStringCurly = '{' + tabName + promptName + ' prompt} - Different number of opening and closing curly brackets detected.\n';
function checkBrackets(evt, textArea, counterElt) {
errorStringParen = '(...) - Different number of opening and closing parentheses detected.\n';
errorStringSquare = '[...] - Different number of opening and closing square brackets detected.\n';
errorStringCurly = '{...} - Different number of opening and closing curly brackets detected.\n';
openBracketRegExp = /\(/g;
closeBracketRegExp = /\)/g;
@ -86,22 +80,31 @@ function checkBrackets(evt) {
}
if(counterElt.title != '') {
counterElt.style = 'color: #FF5555;';
counterElt.classList.add('error');
} else {
counterElt.style = '';
counterElt.classList.remove('error');
}
}
function setupBracketChecking(id_prompt, id_counter){
var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea");
var counter = gradioApp().getElementById(id_counter)
textarea.addEventListener("input", function(evt){
checkBrackets(evt, textarea, counter)
});
}
var shadowRootLoaded = setInterval(function() {
var shadowTextArea = document.querySelector('gradio-app').shadowRoot.querySelectorAll('#txt2img_prompt > label > textarea');
if(shadowTextArea.length < 1) {
return false;
}
var shadowRoot = document.querySelector('gradio-app').shadowRoot;
if(! shadowRoot) return false;
clearInterval(shadowRootLoaded);
var shadowTextArea = shadowRoot.querySelectorAll('#txt2img_prompt > label > textarea');
if(shadowTextArea.length < 1) return false;
document.querySelector('gradio-app').shadowRoot.querySelector('#txt2img_prompt').onkeyup = checkBrackets;
document.querySelector('gradio-app').shadowRoot.querySelector('#txt2img_neg_prompt').onkeyup = checkBrackets;
document.querySelector('gradio-app').shadowRoot.querySelector('#img2img_prompt').onkeyup = checkBrackets;
document.querySelector('gradio-app').shadowRoot.querySelector('#img2img_neg_prompt').onkeyup = checkBrackets;
clearInterval(shadowRootLoaded);
setupBracketChecking('txt2img_prompt', 'txt2img_token_counter')
setupBracketChecking('txt2img_neg_prompt', 'txt2img_negative_token_counter')
setupBracketChecking('img2img_prompt', 'imgimg_token_counter')
setupBracketChecking('img2img_neg_prompt', 'img2img_negative_token_counter')
}, 1000);

50
extensions-builtin/roll-artist/scripts/roll-artist.py
View File

@ -1,50 +0,0 @@
import random
from modules import script_callbacks, shared
import gradio as gr
art_symbol = '\U0001f3a8' # 🎨
global_prompt = None
related_ids = {"txt2img_prompt", "txt2img_clear_prompt", "img2img_prompt", "img2img_clear_prompt" }
def roll_artist(prompt):
allowed_cats = set([x for x in shared.artist_db.categories() if len(shared.opts.random_artist_categories)==0 or x in shared.opts.random_artist_categories])
artist = random.choice([x for x in shared.artist_db.artists if x.category in allowed_cats])
return prompt + ", " + artist.name if prompt != '' else artist.name
def add_roll_button(prompt):
roll = gr.Button(value=art_symbol, elem_id="roll", visible=len(shared.artist_db.artists) > 0)
roll.click(
fn=roll_artist,
_js="update_txt2img_tokens",
inputs=[
prompt,
],
outputs=[
prompt,
]
)
def after_component(component, **kwargs):
global global_prompt
elem_id = kwargs.get('elem_id', None)
if elem_id not in related_ids:
return
if elem_id == "txt2img_prompt":
global_prompt = component
elif elem_id == "txt2img_clear_prompt":
add_roll_button(global_prompt)
elif elem_id == "img2img_prompt":
global_prompt = component
elif elem_id == "img2img_clear_prompt":
add_roll_button(global_prompt)
script_callbacks.on_after_component(after_component)

BIN
html/card-no-preview.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 82 KiB

11
html/extra-networks-card.html Normal file
View File

@ -0,0 +1,11 @@
<div class='card' {preview_html} onclick='return cardClicked({tabname}, {prompt}, {allow_negative_prompt})'>
<div class='actions'>
<div class='additional'>
<ul>
<a href="#" title="replace preview image with currently selected in gallery" onclick='return saveCardPreview(event, {tabname}, {local_preview})'>replace preview</a>
</ul>
</div>
<span class='name'>{name}</span>
</div>
</div>

8
html/extra-networks-no-cards.html Normal file
View File

@ -0,0 +1,8 @@
<div class='nocards'>
<h1>Nothing here. Add some content to the following directories:</h1>
<ul>
{dirs}
</ul>
</div>

9
javascript/aspectRatioOverlay.js
View File

@ -21,11 +21,16 @@ function dimensionChange(e, is_width, is_height){
var targetElement = null;
var tabIndex = get_tab_index('mode_img2img')
if(tabIndex == 0){
if(tabIndex == 0){ // img2img
targetElement = gradioApp().querySelector('div[data-testid=image] img');
} else if(tabIndex == 1){
} else if(tabIndex == 1){ //Sketch
targetElement = gradioApp().querySelector('#img2img_sketch div[data-testid=image] img');
} else if(tabIndex == 2){ // Inpaint
targetElement = gradioApp().querySelector('#img2maskimg div[data-testid=image] img');
} else if(tabIndex == 3){ // Inpaint sketch
targetElement = gradioApp().querySelector('#inpaint_sketch div[data-testid=image] img');
}
if(targetElement){

117
javascript/edit-attention.js
View File

@ -1,75 +1,96 @@
addEventListener('keydown', (event) => {
function keyupEditAttention(event){
let target = event.originalTarget || event.composedPath()[0];
if (!target.matches("#toprow textarea.gr-text-input[placeholder]")) return;
if (!target.matches("[id*='_toprow'] textarea.gr-text-input[placeholder]")) return;
if (! (event.metaKey || event.ctrlKey)) return;
let plus = "ArrowUp"
let minus = "ArrowDown"
if (event.key != plus && event.key != minus) return;
let isPlus = event.key == "ArrowUp"
let isMinus = event.key == "ArrowDown"
if (!isPlus && !isMinus) return;
let selectionStart = target.selectionStart;
let selectionEnd = target.selectionEnd;
// If the user hasn't selected anything, let's select their current parenthesis block
if (selectionStart === selectionEnd) {
let text = target.value;
function selectCurrentParenthesisBlock(OPEN, CLOSE){
if (selectionStart !== selectionEnd) return false;
// Find opening parenthesis around current cursor
const before = target.value.substring(0, selectionStart);
let beforeParen = before.lastIndexOf("(");
if (beforeParen == -1) return;
let beforeParenClose = before.lastIndexOf(")");
const before = text.substring(0, selectionStart);
let beforeParen = before.lastIndexOf(OPEN);
if (beforeParen == -1) return false;
let beforeParenClose = before.lastIndexOf(CLOSE);
while (beforeParenClose !== -1 && beforeParenClose > beforeParen) {
beforeParen = before.lastIndexOf("(", beforeParen - 1);
beforeParenClose = before.lastIndexOf(")", beforeParenClose - 1);
beforeParen = before.lastIndexOf(OPEN, beforeParen - 1);
beforeParenClose = before.lastIndexOf(CLOSE, beforeParenClose - 1);
}
// Find closing parenthesis around current cursor
const after = target.value.substring(selectionStart);
let afterParen = after.indexOf(")");
if (afterParen == -1) return;
let afterParenOpen = after.indexOf("(");
const after = text.substring(selectionStart);
let afterParen = after.indexOf(CLOSE);
if (afterParen == -1) return false;
let afterParenOpen = after.indexOf(OPEN);
while (afterParenOpen !== -1 && afterParen > afterParenOpen) {
afterParen = after.indexOf(")", afterParen + 1);
afterParenOpen = after.indexOf("(", afterParenOpen + 1);
afterParen = after.indexOf(CLOSE, afterParen + 1);
afterParenOpen = after.indexOf(OPEN, afterParenOpen + 1);
}
if (beforeParen === -1 || afterParen === -1) return;
if (beforeParen === -1 || afterParen === -1) return false;
// Set the selection to the text between the parenthesis
const parenContent = target.value.substring(beforeParen + 1, selectionStart + afterParen);
const parenContent = text.substring(beforeParen + 1, selectionStart + afterParen);
const lastColon = parenContent.lastIndexOf(":");
selectionStart = beforeParen + 1;
selectionEnd = selectionStart + lastColon;
target.setSelectionRange(selectionStart, selectionEnd);
}
return true;
}
// If the user hasn't selected anything, let's select their current parenthesis block
if(! selectCurrentParenthesisBlock('<', '>')){
selectCurrentParenthesisBlock('(', ')')
}
event.preventDefault();
if (selectionStart == 0 || target.value[selectionStart - 1] != "(") {
target.value = target.value.slice(0, selectionStart) +
"(" + target.value.slice(selectionStart, selectionEnd) + ":1.0)" +
target.value.slice(selectionEnd);
closeCharacter = ')'
delta = opts.keyedit_precision_attention
target.focus();
target.selectionStart = selectionStart + 1;
target.selectionEnd = selectionEnd + 1;
if (selectionStart > 0 && text[selectionStart - 1] == '<'){
closeCharacter = '>'
delta = opts.keyedit_precision_extra
} else if (selectionStart == 0 || text[selectionStart - 1] != "(") {
} else {
end = target.value.slice(selectionEnd + 1).indexOf(")") + 1;
weight = parseFloat(target.value.slice(selectionEnd + 1, selectionEnd + 1 + end));
if (isNaN(weight)) return;
if (event.key == minus) weight -= 0.1;
if (event.key == plus) weight += 0.1;
// do not include spaces at the end
while(selectionEnd > selectionStart && text[selectionEnd-1] == ' '){
selectionEnd -= 1;
}
if(selectionStart == selectionEnd){
return
}
weight = parseFloat(weight.toPrecision(12));
text = text.slice(0, selectionStart) + "(" + text.slice(selectionStart, selectionEnd) + ":1.0)" + text.slice(selectionEnd);
target.value = target.value.slice(0, selectionEnd + 1) +
weight +
target.value.slice(selectionEnd + 1 + end - 1);
selectionStart += 1;
selectionEnd += 1;
}
target.focus();
target.selectionStart = selectionStart;
target.selectionEnd = selectionEnd;
}
// Since we've modified a Gradio Textbox component manually, we need to simulate an `input` DOM event to ensure its
// internal Svelte data binding remains in sync.
target.dispatchEvent(new Event("input", { bubbles: true }));
});
end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + 1 + end));
if (isNaN(weight)) return;
weight += isPlus ? delta : -delta;
weight = parseFloat(weight.toPrecision(12));
if(String(weight).length == 1) weight += ".0"
text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + 1 + end - 1);
target.focus();
target.value = text;
target.selectionStart = selectionStart;
target.selectionEnd = selectionEnd;
updateInput(target)
}
addEventListener('keydown', (event) => {
keyupEditAttention(event);
});

2
javascript/extensions.js
View File

@ -29,7 +29,7 @@ function install_extension_from_index(button, url){
textarea = gradioApp().querySelector('#extension_to_install textarea')
textarea.value = url
textarea.dispatchEvent(new Event("input", { bubbles: true }))
updateInput(textarea)
gradioApp().querySelector('#install_extension_button').click()
}

69
javascript/extraNetworks.js Normal file
View File

@ -0,0 +1,69 @@
function setupExtraNetworksForTab(tabname){
gradioApp().querySelector('#'+tabname+'_extra_tabs').classList.add('extra-networks')
var tabs = gradioApp().querySelector('#'+tabname+'_extra_tabs > div')
var search = gradioApp().querySelector('#'+tabname+'_extra_search textarea')
var refresh = gradioApp().getElementById(tabname+'_extra_refresh')
var close = gradioApp().getElementById(tabname+'_extra_close')
search.classList.add('search')
tabs.appendChild(search)
tabs.appendChild(refresh)
tabs.appendChild(close)
search.addEventListener("input", function(evt){
searchTerm = search.value.toLowerCase()
gradioApp().querySelectorAll('#'+tabname+'_extra_tabs div.card').forEach(function(elem){
text = elem.querySelector('.name').textContent.toLowerCase()
elem.style.display = text.indexOf(searchTerm) == -1 ? "none" : ""
})
});
}
var activePromptTextarea = {};
function setupExtraNetworks(){
setupExtraNetworksForTab('txt2img')
setupExtraNetworksForTab('img2img')
function registerPrompt(tabname, id){
var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
if (! activePromptTextarea[tabname]){
activePromptTextarea[tabname] = textarea
}
textarea.addEventListener("focus", function(){
activePromptTextarea[tabname] = textarea;
});
}
registerPrompt('txt2img', 'txt2img_prompt')
registerPrompt('txt2img', 'txt2img_neg_prompt')
registerPrompt('img2img', 'img2img_prompt')
registerPrompt('img2img', 'img2img_neg_prompt')
}
onUiLoaded(setupExtraNetworks)
function cardClicked(tabname, textToAdd, allowNegativePrompt){
var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea")
textarea.value = textarea.value + " " + textToAdd
updateInput(textarea)
}
function saveCardPreview(event, tabname, filename){
var textarea = gradioApp().querySelector("#" + tabname + '_preview_filename > label > textarea')
var button = gradioApp().getElementById(tabname + '_save_preview')
textarea.value = filename
updateInput(textarea)
button.click()
event.stopPropagation()
event.preventDefault()
}

10
javascript/hints.js
View File

@ -14,12 +14,14 @@ titles = {
"Seed": "A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result",
"\u{1f3b2}\ufe0f": "Set seed to -1, which will cause a new random number to be used every time",
"\u267b\ufe0f": "Reuse seed from last generation, mostly useful if it was randomed",
"\u{1f3a8}": "Add a random artist to the prompt.",
"\u2199\ufe0f": "Read generation parameters from prompt or last generation if prompt is empty into user interface.",
"\u{1f4c2}": "Open images output directory",
"\u{1f4be}": "Save style",
"\U0001F5D1": "Clear prompt",
"\u{1f4cb}": "Apply selected styles to current prompt",
"\u{1f4d2}": "Paste available values into the field",
"\u{1f3b4}": "Show extra networks",
"Inpaint a part of image": "Draw a mask over an image, and the script will regenerate the masked area with content according to prompt",
"SD upscale": "Upscale image normally, split result into tiles, improve each tile using img2img, merge whole image back",
@ -91,6 +93,7 @@ titles = {
"Weighted sum": "Result = A * (1 - M) + B * M",
"Add difference": "Result = A + (B - C) * M",
"No interpolation": "Result = A",
"Initialization text": "If the number of tokens is more than the number of vectors, some may be skipped.\nLeave the textbox empty to start with zeroed out vectors",
"Learning rate": "How fast should training go. Low values will take longer to train, high values may fail to converge (not generate accurate results) and/or may break the embedding (This has happened if you see Loss: nan in the training info textbox. If this happens, you need to manually restore your embedding from an older not-broken backup).\n\nYou can set a single numeric value, or multiple learning rates using the syntax:\n\n rate_1:max_steps_1, rate_2:max_steps_2, ...\n\nEG: 0.005:100, 1e-3:1000, 1e-5\n\nWill train with rate of 0.005 for first 100 steps, then 1e-3 until 1000 steps, then 1e-5 for all remaining steps.",
@ -104,7 +107,10 @@ titles = {
"Hires steps": "Number of sampling steps for upscaled picture. If 0, uses same as for original.",
"Upscale by": "Adjusts the size of the image by multiplying the original width and height by the selected value. Ignored if either Resize width to or Resize height to are non-zero.",
"Resize width to": "Resizes image to this width. If 0, width is inferred from either of two nearby sliders.",
"Resize height to": "Resizes image to this height. If 0, height is inferred from either of two nearby sliders."
"Resize height to": "Resizes image to this height. If 0, height is inferred from either of two nearby sliders.",
"Multiplier for extra networks": "When adding extra network such as Hypernetwork or Lora to prompt, use this multiplier for it.",
"Discard weights with matching name": "Regular expression; if weights's name matches it, the weights is not written to the resulting checkpoint. Use ^model_ema to discard EMA weights.",
"Extra networks tab order": "Comma-separated list of tab names; tabs listed here will appear in the extra networks UI first and in order lsited."
}

3
javascript/hires_fix.js
View File

@ -1,6 +1,5 @@
function setInactive(elem, inactive){
console.log(elem)
if(inactive){
elem.classList.add('inactive')
} else{
@ -9,8 +8,6 @@ function setInactive(elem, inactive){
}
function onCalcResolutionHires(enable, width, height, hr_scale, hr_resize_x, hr_resize_y){
console.log(enable, width, height, hr_scale, hr_resize_x, hr_resize_y)
hrUpscaleBy = gradioApp().getElementById('txt2img_hr_scale')
hrResizeX = gradioApp().getElementById('txt2img_hr_resize_x')
hrResizeY = gradioApp().getElementById('txt2img_hr_resize_y')

10
javascript/imageviewer.js
View File

@ -148,7 +148,15 @@ function showGalleryImage() {
if(e && e.parentElement.tagName == 'DIV'){
e.style.cursor='pointer'
e.style.userSelect='none'
e.addEventListener('mousedown', function (evt) {
var isFirefox = isFirefox = navigator.userAgent.toLowerCase().indexOf('firefox') > -1
// For Firefox, listening on click first switched to next image then shows the lightbox.
// If you know how to fix this without switching to mousedown event, please.
// For other browsers the event is click to make it possiblr to drag picture.
var event = isFirefox ? 'mousedown' : 'click'
e.addEventListener(event, function (evt) {
if(!opts.js_modal_lightbox || evt.button != 0) return;
modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed)
evt.preventDefault()

6
javascript/localization.js
View File

@ -10,10 +10,8 @@ ignore_ids_for_localization={
modelmerger_tertiary_model_name: 'OPTION',
train_embedding: 'OPTION',
train_hypernetwork: 'OPTION',
txt2img_style_index: 'OPTION',
txt2img_style2_index: 'OPTION',
img2img_style_index: 'OPTION',
img2img_style2_index: 'OPTION',
txt2img_styles: 'OPTION',
img2img_styles: 'OPTION',
setting_random_artist_categories: 'SPAN',
setting_face_restoration_model: 'SPAN',
setting_realesrgan_enabled_models: 'SPAN',

280
javascript/progressbar.js
View File

@ -1,82 +1,25 @@
// code related to showing and updating progressbar shown as the image is being made
global_progressbars = {}
galleries = {}
storedGallerySelections = {}
galleryObservers = {}
// this tracks launches of window.setTimeout for progressbar to prevent starting a new timeout when the previous is still running
timeoutIds = {}
function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip, id_interrupt, id_preview, id_gallery){
// gradio 3.8's enlightened approach allows them to create two nested div elements inside each other with same id
// every time you use gr.HTML(elem_id='xxx'), so we handle this here
var progressbar = gradioApp().querySelector("#"+id_progressbar+" #"+id_progressbar)
var progressbarParent
if(progressbar){
progressbarParent = gradioApp().querySelector("#"+id_progressbar)
} else{
progressbar = gradioApp().getElementById(id_progressbar)
progressbarParent = null
}
var skip = id_skip ? gradioApp().getElementById(id_skip) : null
var interrupt = gradioApp().getElementById(id_interrupt)
if(opts.show_progress_in_title && progressbar && progressbar.offsetParent){
if(progressbar.innerText){
let newtitle = '[' + progressbar.innerText.trim() + '] Stable Diffusion';
if(document.title != newtitle){
document.title = newtitle;
}
}else{
let newtitle = 'Stable Diffusion'
if(document.title != newtitle){
document.title = newtitle;
}
}
}
if(progressbar!= null && progressbar != global_progressbars[id_progressbar]){
global_progressbars[id_progressbar] = progressbar
var mutationObserver = new MutationObserver(function(m){
if(timeoutIds[id_part]) return;
preview = gradioApp().getElementById(id_preview)
gallery = gradioApp().getElementById(id_gallery)
if(preview != null && gallery != null){
preview.style.width = gallery.clientWidth + "px"
preview.style.height = gallery.clientHeight + "px"
if(progressbarParent) progressbar.style.width = progressbarParent.clientWidth + "px"
//only watch gallery if there is a generation process going on
check_gallery(id_gallery);
var progressDiv = gradioApp().querySelectorAll('#' + id_progressbar_span).length > 0;
if(progressDiv){
timeoutIds[id_part] = window.setTimeout(function() {
timeoutIds[id_part] = null
requestMoreProgress(id_part, id_progressbar_span, id_skip, id_interrupt)
}, 500)
} else{
if (skip) {
skip.style.display = "none"
}
interrupt.style.display = "none"
//disconnect observer once generation finished, so user can close selected image if they want
if (galleryObservers[id_gallery]) {
galleryObservers[id_gallery].disconnect();
galleries[id_gallery] = null;
}
}
}
});
mutationObserver.observe( progressbar, { childList:true, subtree:true })
}
function rememberGallerySelection(id_gallery){
storedGallerySelections[id_gallery] = getGallerySelectedIndex(id_gallery)
}
function getGallerySelectedIndex(id_gallery){
let galleryButtons = gradioApp().querySelectorAll('#'+id_gallery+' .gallery-item')
let galleryBtnSelected = gradioApp().querySelector('#'+id_gallery+' .gallery-item.\\!ring-2')
let currentlySelectedIndex = -1
galleryButtons.forEach(function(v, i){ if(v==galleryBtnSelected) { currentlySelectedIndex = i } })
return currentlySelectedIndex
}
// this is a workaround for https://github.com/gradio-app/gradio/issues/2984
function check_gallery(id_gallery){
let gallery = gradioApp().getElementById(id_gallery)
// if gallery has no change, no need to setting up observer again.
@ -85,10 +28,16 @@ function check_gallery(id_gallery){
if(galleryObservers[id_gallery]){
galleryObservers[id_gallery].disconnect();
}
let prevSelectedIndex = selected_gallery_index();
storedGallerySelections[id_gallery] = -1
galleryObservers[id_gallery] = new MutationObserver(function (){
let galleryButtons = gradioApp().querySelectorAll('#'+id_gallery+' .gallery-item')
let galleryBtnSelected = gradioApp().querySelector('#'+id_gallery+' .gallery-item.\\!ring-2')
let currentlySelectedIndex = getGallerySelectedIndex(id_gallery)
prevSelectedIndex = storedGallerySelections[id_gallery]
storedGallerySelections[id_gallery] = -1
if (prevSelectedIndex !== -1 && galleryButtons.length>prevSelectedIndex && !galleryBtnSelected) {
// automatically re-open previously selected index (if exists)
activeElement = gradioApp().activeElement;
@ -120,30 +69,175 @@ function check_gallery(id_gallery){
}
onUiUpdate(function(){
check_progressbar('txt2img', 'txt2img_progressbar', 'txt2img_progress_span', 'txt2img_skip', 'txt2img_interrupt', 'txt2img_preview', 'txt2img_gallery')
check_progressbar('img2img', 'img2img_progressbar', 'img2img_progress_span', 'img2img_skip', 'img2img_interrupt', 'img2img_preview', 'img2img_gallery')
check_progressbar('ti', 'ti_progressbar', 'ti_progress_span', '', 'ti_interrupt', 'ti_preview', 'ti_gallery')
check_gallery('txt2img_gallery')
check_gallery('img2img_gallery')
})
function requestMoreProgress(id_part, id_progressbar_span, id_skip, id_interrupt){
btn = gradioApp().getElementById(id_part+"_check_progress");
if(btn==null) return;
btn.click();
var progressDiv = gradioApp().querySelectorAll('#' + id_progressbar_span).length > 0;
var skip = id_skip ? gradioApp().getElementById(id_skip) : null
var interrupt = gradioApp().getElementById(id_interrupt)
if(progressDiv && interrupt){
if (skip) {
skip.style.display = "block"
function request(url, data, handler, errorHandler){
var xhr = new XMLHttpRequest();
var url = url;
xhr.open("POST", url, true);
xhr.setRequestHeader("Content-Type", "application/json");
xhr.onreadystatechange = function () {
if (xhr.readyState === 4) {
if (xhr.status === 200) {
try {
var js = JSON.parse(xhr.responseText);
handler(js)
} catch (error) {
console.error(error);
errorHandler()
}
} else{
errorHandler()
}
}
interrupt.style.display = "block"
};
var js = JSON.stringify(data);
xhr.send(js);
}
function pad2(x){
return x<10 ? '0'+x : x
}
function formatTime(secs){
if(secs > 3600){
return pad2(Math.floor(secs/60/60)) + ":" + pad2(Math.floor(secs/60)%60) + ":" + pad2(Math.floor(secs)%60)
} else if(secs > 60){
return pad2(Math.floor(secs/60)) + ":" + pad2(Math.floor(secs)%60)
} else{
return Math.floor(secs) + "s"
}
}
function requestProgress(id_part){
btn = gradioApp().getElementById(id_part+"_check_progress_initial");
if(btn==null) return;
function setTitle(progress){
var title = 'Stable Diffusion'
btn.click();
if(opts.show_progress_in_title && progress){
title = '[' + progress.trim() + '] ' + title;
}
if(document.title != title){
document.title = title;
}
}
function randomId(){
return "task(" + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7)+")"
}
// starts sending progress requests to "/internal/progress" uri, creating progressbar above progressbarContainer element and
// preview inside gallery element. Cleans up all created stuff when the task is over and calls atEnd.
// calls onProgress every time there is a progress update
function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgress){
var dateStart = new Date()
var wasEverActive = false
var parentProgressbar = progressbarContainer.parentNode
var parentGallery = gallery ? gallery.parentNode : null
var divProgress = document.createElement('div')
divProgress.className='progressDiv'
divProgress.style.display = opts.show_progressbar ? "" : "none"
var divInner = document.createElement('div')
divInner.className='progress'
divProgress.appendChild(divInner)
parentProgressbar.insertBefore(divProgress, progressbarContainer)
if(parentGallery){
var livePreview = document.createElement('div')
livePreview.className='livePreview'
parentGallery.insertBefore(livePreview, gallery)
}
var removeProgressBar = function(){
setTitle("")
parentProgressbar.removeChild(divProgress)
if(parentGallery) parentGallery.removeChild(livePreview)
atEnd()
}
var fun = function(id_task, id_live_preview){
request("./internal/progress", {"id_task": id_task, "id_live_preview": id_live_preview}, function(res){
if(res.completed){
removeProgressBar()
return
}
var rect = progressbarContainer.getBoundingClientRect()
if(rect.width){
divProgress.style.width = rect.width + "px";
}
progressText = ""
divInner.style.width = ((res.progress || 0) * 100.0) + '%'
divInner.style.background = res.progress ? "" : "transparent"
if(res.progress > 0){
progressText = ((res.progress || 0) * 100.0).toFixed(0) + '%'
}
if(res.eta){
progressText += " ETA: " + formatTime(res.eta)
}
setTitle(progressText)
if(res.textinfo && res.textinfo.indexOf("\n") == -1){
progressText = res.textinfo + " " + progressText
}
divInner.textContent = progressText
var elapsedFromStart = (new Date() - dateStart) / 1000
if(res.active) wasEverActive = true;
if(! res.active && wasEverActive){
removeProgressBar()
return
}
if(elapsedFromStart > 5 && !res.queued && !res.active){
removeProgressBar()
return
}
if(res.live_preview && gallery){
var rect = gallery.getBoundingClientRect()
if(rect.width){
livePreview.style.width = rect.width + "px"
livePreview.style.height = rect.height + "px"
}
var img = new Image();
img.onload = function() {
livePreview.appendChild(img)
if(livePreview.childElementCount > 2){
livePreview.removeChild(livePreview.firstElementChild)
}
}
img.src = res.live_preview;
}
if(onProgress){
onProgress(res)
}
setTimeout(() => {
fun(id_task, res.id_live_preview);
}, opts.live_preview_refresh_period || 500)
}, function(){
removeProgressBar()
})
}
fun(id_task, 0)
}

13
javascript/textualInversion.js
View File

@ -1,8 +1,17 @@
function start_training_textual_inversion(){
requestProgress('ti')
gradioApp().querySelector('#ti_error').innerHTML=''
return args_to_array(arguments)
var id = randomId()
requestProgress(id, gradioApp().getElementById('ti_output'), gradioApp().getElementById('ti_gallery'), function(){}, function(progress){
gradioApp().getElementById('ti_progress').innerHTML = progress.textinfo
})
var res = args_to_array(arguments)
res[0] = id
return res
}

118
javascript/ui.js
View File

@ -45,10 +45,27 @@ function switch_to_txt2img(){
return args_to_array(arguments);
}
function switch_to_img2img(){
function switch_to_img2img_tab(no){
gradioApp().querySelector('#tabs').querySelectorAll('button')[1].click();
gradioApp().getElementById('mode_img2img').querySelectorAll('button')[0].click();
gradioApp().getElementById('mode_img2img').querySelectorAll('button')[no].click();
}
function switch_to_img2img(){
switch_to_img2img_tab(0);
return args_to_array(arguments);
}
function switch_to_sketch(){
switch_to_img2img_tab(1);
return args_to_array(arguments);
}
function switch_to_inpaint(){
switch_to_img2img_tab(2);
return args_to_array(arguments);
}
function switch_to_inpaint_sketch(){
switch_to_img2img_tab(3);
return args_to_array(arguments);
}
@ -92,6 +109,13 @@ function get_extras_tab_index(){
return [get_tab_index('mode_extras'), get_tab_index('extras_resize_mode'), ...args]
}
function get_img2img_tab_index() {
let res = args_to_array(arguments)
res.splice(-2)
res[0] = get_tab_index('mode_img2img')
return res
}
function create_submit_args(args){
res = []
for(var i=0;i<args.length;i++){
@ -109,19 +133,51 @@ function create_submit_args(args){
return res
}
function submit(){
requestProgress('txt2img')
function showSubmitButtons(tabname, show){
gradioApp().getElementById(tabname+'_interrupt').style.display = show ? "none" : "block"
gradioApp().getElementById(tabname+'_skip').style.display = show ? "none" : "block"
}
return create_submit_args(arguments)
function submit(){
rememberGallerySelection('txt2img_gallery')
showSubmitButtons('txt2img', false)
var id = randomId()
requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function(){
showSubmitButtons('txt2img', true)
})
var res = create_submit_args(arguments)
res[0] = id
return res
}
function submit_img2img(){
requestProgress('img2img')
rememberGallerySelection('img2img_gallery')
showSubmitButtons('img2img', false)
res = create_submit_args(arguments)
var id = randomId()
requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function(){
showSubmitButtons('img2img', true)
})
res[0] = get_tab_index('mode_img2img')
var res = create_submit_args(arguments)
res[0] = id
res[1] = get_tab_index('mode_img2img')
return res
}
function modelmerger(){
var id = randomId()
requestProgress(id, gradioApp().getElementById('modelmerger_results_panel'), null, function(){})
var res = create_submit_args(arguments)
res[0] = id
return res
}
@ -140,8 +196,6 @@ function confirm_clear_prompt(prompt, negative_prompt) {
return [prompt, negative_prompt]
}
opts = {}
onUiUpdate(function(){
if(Object.keys(opts).length != 0) return;
@ -149,8 +203,8 @@ onUiUpdate(function(){
json_elem = gradioApp().getElementById('settings_json')
if(json_elem == null) return;
textarea = json_elem.querySelector('textarea')
jsdata = textarea.value
var textarea = json_elem.querySelector('textarea')
var jsdata = textarea.value
opts = JSON.parse(jsdata)
executeCallbacks(optionsChangedCallbacks);
@ -174,14 +228,29 @@ onUiUpdate(function(){
json_elem.parentElement.style.display="none"
if (!txt2img_textarea) {
txt2img_textarea = gradioApp().querySelector("#txt2img_prompt > label > textarea");
txt2img_textarea?.addEventListener("input", () => update_token_counter("txt2img_token_button"));
}
if (!img2img_textarea) {
img2img_textarea = gradioApp().querySelector("#img2img_prompt > label > textarea");
img2img_textarea?.addEventListener("input", () => update_token_counter("img2img_token_button"));
}
function registerTextarea(id, id_counter, id_button){
var prompt = gradioApp().getElementById(id)
var counter = gradioApp().getElementById(id_counter)
var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
if(counter.parentElement == prompt.parentElement){
return
}
prompt.parentElement.insertBefore(counter, prompt)
counter.classList.add("token-counter")
prompt.parentElement.style.position = "relative"
textarea.addEventListener("input", function(){
update_token_counter(id_button);
});
}
registerTextarea('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button')
registerTextarea('txt2img_neg_prompt', 'txt2img_negative_token_counter', 'txt2img_negative_token_button')
registerTextarea('img2img_prompt', 'img2img_token_counter', 'img2img_token_button')
registerTextarea('img2img_neg_prompt', 'img2img_negative_token_counter', 'img2img_negative_token_button')
show_all_pages = gradioApp().getElementById('settings_show_all_pages')
settings_tabs = gradioApp().querySelector('#settings div')
@ -195,7 +264,6 @@ onUiUpdate(function(){
}
})
onOptionsChanged(function(){
elem = gradioApp().getElementById('sd_checkpoint_hash')
sd_checkpoint_hash = opts.sd_checkpoint_hash || ""
@ -238,3 +306,11 @@ function restart_reload(){
return []
}
// Simulate an `input` DOM event for Gradio Textbox component. Needed after you edit its contents in javascript, otherwise your edits
// will only visible on web page and not sent to python.
function updateInput(target){
let e = new Event("input", { bubbles: true })
Object.defineProperty(e, "target", {value: target})
target.dispatchEvent(e);
}

9
launch.py
View File

@ -14,6 +14,7 @@ python = sys.executable
git = os.environ.get('GIT', "git")
index_url = os.environ.get('INDEX_URL', "")
stored_commit_hash = None
skip_install = False
def commit_hash():
@ -89,6 +90,9 @@ def run_python(code, desc=None, errdesc=None):
def run_pip(args, desc=None):
if skip_install:
return
index_url_line = f' --index-url {index_url}' if index_url != '' else ''
return run(f'"{python}" -m pip {args} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}")
@ -173,6 +177,8 @@ def run_extensions_installers(settings_file):
def prepare_environment():
global skip_install
torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113")
requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
@ -206,6 +212,7 @@ def prepare_environment():
sys.argv, reinstall_xformers = extract_arg(sys.argv, '--reinstall-xformers')
sys.argv, update_check = extract_arg(sys.argv, '--update-check')
sys.argv, run_tests, test_dir = extract_opt(sys.argv, '--tests')
sys.argv, skip_install = extract_arg(sys.argv, '--skip-install')
xformers = '--xformers' in sys.argv
ngrok = '--ngrok' in sys.argv
@ -279,6 +286,8 @@ def tests(test_dir):
sys.argv.append("./test/test_files/empty.pt")
if "--skip-torch-cuda-test" not in sys.argv:
sys.argv.append("--skip-torch-cuda-test")
if "--disable-nan-check" not in sys.argv:
sys.argv.append("--disable-nan-check")
print(f"Launching Web UI in another process for testing with arguments: {' '.join(sys.argv[1:])}")

15
modules/api/api.py
View File

@ -126,8 +126,6 @@ class Api:
self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem])
self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem])
self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem])
self.add_api_route("/sdapi/v1/artist-categories", self.get_artists_categories, methods=["GET"], response_model=List[str])
self.add_api_route("/sdapi/v1/artists", self.get_artists, methods=["GET"], response_model=List[ArtistItem])
self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=EmbeddingsResponse)
self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"])
self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=CreateResponse)
@ -390,12 +388,6 @@ class Api:
return styleList
def get_artists_categories(self):
return shared.artist_db.cats
def get_artists(self):
return [{"name":x[0], "score":x[1], "category":x[2]} for x in shared.artist_db.artists]
def get_embeddings(self):
db = sd_hijack.model_hijack.embedding_db
@ -480,7 +472,7 @@ class Api:
def train_hypernetwork(self, args: dict):
try:
shared.state.begin()
initial_hypernetwork = shared.loaded_hypernetwork
shared.loaded_hypernetworks = []
apply_optimizations = shared.opts.training_xattention_optimizations
error = None
filename = ''
@ -491,16 +483,15 @@ class Api:
except Exception as e:
error = e
finally:
shared.loaded_hypernetwork = initial_hypernetwork
shared.sd_model.cond_stage_model.to(devices.device)
shared.sd_model.first_stage_model.to(devices.device)
if not apply_optimizations:
sd_hijack.apply_optimizations()
shared.state.end()
return TrainResponse(info = "train embedding complete: filename: {filename} error: {error}".format(filename = filename, error = error))
return TrainResponse(info="train embedding complete: filename: {filename} error: {error}".format(filename=filename, error=error))
except AssertionError as msg:
shared.state.end()
return TrainResponse(info = "train embedding error: {error}".format(error = error))
return TrainResponse(info="train embedding error: {error}".format(error=error))
def get_memory(self):
try:

25
modules/artists.py
View File

@ -1,25 +0,0 @@
import os.path
import csv
from collections import namedtuple
Artist = namedtuple("Artist", ['name', 'weight', 'category'])
class ArtistsDatabase:
def __init__(self, filename):
self.cats = set()
self.artists = []
if not os.path.exists(filename):
return
with open(filename, "r", newline='', encoding="utf8") as file:
reader = csv.DictReader(file)
for row in reader:
artist = Artist(row["artist"], float(row["score"]), row["category"])
self.artists.append(artist)
self.cats.add(artist.category)
def categories(self):
return sorted(self.cats)

19
modules/call_queue.py
View File

@ -4,7 +4,7 @@ import threading
import traceback
import time
from modules import shared
from modules import shared, progress
queue_lock = threading.Lock()
@ -22,12 +22,23 @@ def wrap_queued_call(func):
def wrap_gradio_gpu_call(func, extra_outputs=None):
def f(*args, **kwargs):
shared.state.begin()
# if the first argument is a string that says "task(...)", it is treated as a job id
if len(args) > 0 and type(args[0]) == str and args[0][0:5] == "task(" and args[0][-1] == ")":
id_task = args[0]
progress.add_task_to_queue(id_task)
else:
id_task = None
with queue_lock:
res = func(*args, **kwargs)
shared.state.begin()
progress.start_task(id_task)
shared.state.end()
try:
res = func(*args, **kwargs)
finally:
progress.finish_task(id_task)
shared.state.end()
return res

42
modules/devices.py
View File

@ -106,6 +106,36 @@ def autocast(disable=False):
return torch.autocast("cuda")
class NansException(Exception):
pass
def test_for_nans(x, where):
from modules import shared
if shared.cmd_opts.disable_nan_check:
return
if not torch.all(torch.isnan(x)).item():
return
if where == "unet":
message = "A tensor with all NaNs was produced in Unet."
if not shared.cmd_opts.no_half:
message += " This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try using --no-half commandline argument to fix this."
elif where == "vae":
message = "A tensor with all NaNs was produced in VAE."
if not shared.cmd_opts.no_half and not shared.cmd_opts.no_half_vae:
message += " This could be because there's not enough precision to represent the picture. Try adding --no-half-vae commandline argument to fix this."
else:
message = "A tensor with all NaNs was produced."
raise NansException(message)
# MPS workaround for https://github.com/pytorch/pytorch/issues/79383
orig_tensor_to = torch.Tensor.to
def tensor_to_fix(self, *args, **kwargs):
@ -139,8 +169,10 @@ orig_Tensor_cumsum = torch.Tensor.cumsum
def cumsum_fix(input, cumsum_func, *args, **kwargs):
if input.device.type == 'mps':
output_dtype = kwargs.get('dtype', input.dtype)
if any(output_dtype == broken_dtype for broken_dtype in [torch.bool, torch.int8, torch.int16, torch.int64]):
if output_dtype == torch.int64:
return cumsum_func(input.cpu(), *args, **kwargs).to(input.device)
elif cumsum_needs_bool_fix and output_dtype == torch.bool or cumsum_needs_int_fix and (output_dtype == torch.int8 or output_dtype == torch.int16):
return cumsum_func(input.to(torch.int32), *args, **kwargs).to(torch.int64)
return cumsum_func(input, *args, **kwargs)
@ -151,8 +183,10 @@ if has_mps():
torch.nn.functional.layer_norm = layer_norm_fix
torch.Tensor.numpy = numpy_fix
elif version.parse(torch.__version__) > version.parse("1.13.1"):
if not torch.Tensor([1,2]).to(torch.device("mps")).equal(torch.Tensor([1,1]).to(torch.device("mps")).cumsum(0, dtype=torch.int16)):
torch.cumsum = lambda input, *args, **kwargs: ( cumsum_fix(input, orig_cumsum, *args, **kwargs) )
torch.Tensor.cumsum = lambda self, *args, **kwargs: ( cumsum_fix(self, orig_Tensor_cumsum, *args, **kwargs) )
cumsum_needs_int_fix = not torch.Tensor([1,2]).to(torch.device("mps")).equal(torch.ShortTensor([1,1]).to(torch.device("mps")).cumsum(0))
cumsum_needs_bool_fix = not torch.BoolTensor([True,True]).to(device=torch.device("mps"), dtype=torch.int64).equal(torch.BoolTensor([True,False]).to(torch.device("mps")).cumsum(0))
torch.cumsum = lambda input, *args, **kwargs: ( cumsum_fix(input, orig_cumsum, *args, **kwargs) )
torch.Tensor.cumsum = lambda self, *args, **kwargs: ( cumsum_fix(self, orig_Tensor_cumsum, *args, **kwargs) )
orig_narrow = torch.narrow
torch.narrow = lambda *args, **kwargs: ( orig_narrow(*args, **kwargs).clone() )

2
modules/errors.py
View File

@ -19,7 +19,7 @@ def display(e: Exception, task):
message = str(e)
if "copying a param with shape torch.Size([640, 1024]) from checkpoint, the shape in current model is torch.Size([640, 768])" in message:
print_error_explanation("""
The most likely cause of this is you are trying to load Stable Diffusion 2.0 model without specifying its connfig file.
The most likely cause of this is you are trying to load Stable Diffusion 2.0 model without specifying its config file.
See https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20 for how to solve this.
""")

147
modules/extra_networks.py Normal file
View File

@ -0,0 +1,147 @@
import re
from collections import defaultdict
from modules import errors
extra_network_registry = {}
def initialize():
extra_network_registry.clear()
def register_extra_network(extra_network):
extra_network_registry[extra_network.name] = extra_network
class ExtraNetworkParams:
def __init__(self, items=None):
self.items = items or []
class ExtraNetwork:
def __init__(self, name):
self.name = name
def activate(self, p, params_list):
"""
Called by processing on every run. Whatever the extra network is meant to do should be activated here.
Passes arguments related to this extra network in params_list.
User passes arguments by specifying this in his prompt:
<name:arg1:arg2:arg3>
Where name matches the name of this ExtraNetwork object, and arg1:arg2:arg3 are any natural number of text arguments
separated by colon.
Even if the user does not mention this ExtraNetwork in his prompt, the call will stil be made, with empty params_list -
in this case, all effects of this extra networks should be disabled.
Can be called multiple times before deactivate() - each new call should override the previous call completely.
For example, if this ExtraNetwork's name is 'hypernet' and user's prompt is:
> "1girl, <hypernet:agm:1.1> <extrasupernet:master:12:13:14> <hypernet:ray>"
params_list will be:
[
ExtraNetworkParams(items=["agm", "1.1"]),
ExtraNetworkParams(items=["ray"])
]
"""
raise NotImplementedError
def deactivate(self, p):
"""
Called at the end of processing for housekeeping. No need to do anything here.
"""
raise NotImplementedError
def activate(p, extra_network_data):
"""call activate for extra networks in extra_network_data in specified order, then call
activate for all remaining registered networks with an empty argument list"""
for extra_network_name, extra_network_args in extra_network_data.items():
extra_network = extra_network_registry.get(extra_network_name, None)
if extra_network is None:
print(f"Skipping unknown extra network: {extra_network_name}")
continue
try:
extra_network.activate(p, extra_network_args)
except Exception as e:
errors.display(e, f"activating extra network {extra_network_name} with arguments {extra_network_args}")
for extra_network_name, extra_network in extra_network_registry.items():
args = extra_network_data.get(extra_network_name, None)
if args is not None:
continue
try:
extra_network.activate(p, [])
except Exception as e:
errors.display(e, f"activating extra network {extra_network_name}")
def deactivate(p, extra_network_data):
"""call deactivate for extra networks in extra_network_data in specified order, then call
deactivate for all remaining registered networks"""
for extra_network_name, extra_network_args in extra_network_data.items():
extra_network = extra_network_registry.get(extra_network_name, None)
if extra_network is None:
continue
try:
extra_network.deactivate(p)
except Exception as e:
errors.display(e, f"deactivating extra network {extra_network_name}")
for extra_network_name, extra_network in extra_network_registry.items():
args = extra_network_data.get(extra_network_name, None)
if args is not None:
continue
try:
extra_network.deactivate(p)
except Exception as e:
errors.display(e, f"deactivating unmentioned extra network {extra_network_name}")
re_extra_net = re.compile(r"<(\w+):([^>]+)>")
def parse_prompt(prompt):
res = defaultdict(list)
def found(m):
name = m.group(1)
args = m.group(2)
res[name].append(ExtraNetworkParams(items=args.split(":")))
return ""
prompt = re.sub(re_extra_net, found, prompt)
return prompt, res
def parse_prompts(prompts):
res = []
extra_data = None
for prompt in prompts:
updated_prompt, parsed_extra_data = parse_prompt(prompt)
if extra_data is None:
extra_data = parsed_extra_data
res.append(updated_prompt)
return res, extra_data

21
modules/extra_networks_hypernet.py Normal file
View File

@ -0,0 +1,21 @@
from modules import extra_networks
from modules.hypernetworks import hypernetwork
class ExtraNetworkHypernet(extra_networks.ExtraNetwork):
def __init__(self):
super().__init__('hypernet')
def activate(self, p, params_list):
names = []
multipliers = []
for params in params_list:
assert len(params.items) > 0
names.append(params.items[0])
multipliers.append(float(params.items[1]) if len(params.items) > 1 else 1.0)
hypernetwork.load_hypernetworks(names, multipliers)
def deactivate(self, p):
pass

157
modules/extras.py
View File

@ -1,6 +1,7 @@
from __future__ import annotations
import math
import os
import re
import sys
import traceback
import shutil
@ -15,7 +16,7 @@ from typing import Callable, List, OrderedDict, Tuple
from functools import partial
from dataclasses import dataclass
from modules import processing, shared, images, devices, sd_models, sd_samplers
from modules import processing, shared, images, devices, sd_models, sd_samplers, sd_vae
from modules.shared import opts
import modules.gfpgan_model
from modules.ui import plaintext_to_html
@ -251,7 +252,8 @@ def run_pnginfo(image):
def create_config(ckpt_result, config_source, a, b, c):
def config(x):
return sd_models.find_checkpoint_config(x) if x else None
res = sd_models.find_checkpoint_config(x) if x else None
return res if res != shared.sd_default_config else None
if config_source == 0:
cfg = config(a) or config(b) or config(c)
@ -274,10 +276,25 @@ def create_config(ckpt_result, config_source, a, b, c):
shutil.copyfile(cfg, checkpoint_filename)
def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source):
checkpoint_dict_skip_on_merge = ["cond_stage_model.transformer.text_model.embeddings.position_ids"]
def to_half(tensor, enable):
if enable and tensor.dtype == torch.float:
return tensor.half()
return tensor
def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights):
shared.state.begin()
shared.state.job = 'model-merge'
def fail(message):
shared.state.textinfo = message
shared.state.end()
return [*[gr.update() for _ in range(4)], message]
def weighted_sum(theta0, theta1, alpha):
return ((1 - alpha) * theta0) + (alpha * theta1)
@ -287,51 +304,96 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
def add_difference(theta0, theta1_2_diff, alpha):
return theta0 + (alpha * theta1_2_diff)
primary_model_info = sd_models.checkpoints_list[primary_model_name]
secondary_model_info = sd_models.checkpoints_list[secondary_model_name]
tertiary_model_info = sd_models.checkpoints_list.get(tertiary_model_name, None)
result_is_inpainting_model = False
def filename_weighted_sum():
a = primary_model_info.model_name
b = secondary_model_info.model_name
Ma = round(1 - multiplier, 2)
Mb = round(multiplier, 2)
return f"{Ma}({a}) + {Mb}({b})"
def filename_add_difference():
a = primary_model_info.model_name
b = secondary_model_info.model_name
c = tertiary_model_info.model_name
M = round(multiplier, 2)
return f"{a} + {M}({b} - {c})"
def filename_nothing():
return primary_model_info.model_name
theta_funcs = {
"Weighted sum": (None, weighted_sum),
"Add difference": (get_difference, add_difference),
"Weighted sum": (filename_weighted_sum, None, weighted_sum),
"Add difference": (filename_add_difference, get_difference, add_difference),
"No interpolation": (filename_nothing, None, None),
}
theta_func1, theta_func2 = theta_funcs[interp_method]
filename_generator, theta_func1, theta_func2 = theta_funcs[interp_method]
shared.state.job_count = (1 if theta_func1 else 0) + (1 if theta_func2 else 0)
if theta_func1 and not tertiary_model_info:
shared.state.textinfo = "Failed: Interpolation method requires a tertiary model."
shared.state.end()
return ["Failed: Interpolation method requires a tertiary model."] + [gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)]
if not primary_model_name:
return fail("Failed: Merging requires a primary model.")
shared.state.textinfo = f"Loading {secondary_model_info.filename}..."
print(f"Loading {secondary_model_info.filename}...")
theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu')
primary_model_info = sd_models.checkpoints_list[primary_model_name]
if theta_func2 and not secondary_model_name:
return fail("Failed: Merging requires a secondary model.")
secondary_model_info = sd_models.checkpoints_list[secondary_model_name] if theta_func2 else None
if theta_func1 and not tertiary_model_name:
return fail(f"Failed: Interpolation method ({interp_method}) requires a tertiary model.")
tertiary_model_info = sd_models.checkpoints_list[tertiary_model_name] if theta_func1 else None
result_is_inpainting_model = False
if theta_func2:
shared.state.textinfo = f"Loading B"
print(f"Loading {secondary_model_info.filename}...")
theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu')
else:
theta_1 = None
if theta_func1:
shared.state.textinfo = f"Loading C"
print(f"Loading {tertiary_model_info.filename}...")
theta_2 = sd_models.read_state_dict(tertiary_model_info.filename, map_location='cpu')
shared.state.textinfo = 'Merging B and C'
shared.state.sampling_steps = len(theta_1.keys())
for key in tqdm.tqdm(theta_1.keys()):
if key in checkpoint_dict_skip_on_merge:
continue
if 'model' in key:
if key in theta_2:
t2 = theta_2.get(key, torch.zeros_like(theta_1[key]))
theta_1[key] = theta_func1(theta_1[key], t2)
else:
theta_1[key] = torch.zeros_like(theta_1[key])
shared.state.sampling_step += 1
del theta_2
shared.state.nextjob()
shared.state.textinfo = f"Loading {primary_model_info.filename}..."
print(f"Loading {primary_model_info.filename}...")
theta_0 = sd_models.read_state_dict(primary_model_info.filename, map_location='cpu')
print("Merging...")
shared.state.textinfo = 'Merging A and B'
shared.state.sampling_steps = len(theta_0.keys())
for key in tqdm.tqdm(theta_0.keys()):
if 'model' in key and key in theta_1:
if theta_1 and 'model' in key and key in theta_1:
if key in checkpoint_dict_skip_on_merge:
continue
a = theta_0[key]
b = theta_1[key]
shared.state.textinfo = f'Merging layer {key}'
# this enables merging an inpainting model (A) with another one (B);
# where normal model would have 4 channels, for latenst space, inpainting model would
# have another 4 channels for unmasked picture's latent space, plus one channel for mask, for a total of 9
@ -346,32 +408,45 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
else:
theta_0[key] = theta_func2(a, b, multiplier)
if save_as_half:
theta_0[key] = theta_0[key].half()
theta_0[key] = to_half(theta_0[key], save_as_half)
shared.state.sampling_step += 1
# I believe this part should be discarded, but I'll leave it for now until I am sure
for key in theta_1.keys():
if 'model' in key and key not in theta_0:
theta_0[key] = theta_1[key]
if save_as_half:
theta_0[key] = theta_0[key].half()
del theta_1
bake_in_vae_filename = sd_vae.vae_dict.get(bake_in_vae, None)
if bake_in_vae_filename is not None:
print(f"Baking in VAE from {bake_in_vae_filename}")
shared.state.textinfo = 'Baking in VAE'
vae_dict = sd_vae.load_vae_dict(bake_in_vae_filename, map_location='cpu')
for key in vae_dict.keys():
theta_0_key = 'first_stage_model.' + key
if theta_0_key in theta_0:
theta_0[theta_0_key] = to_half(vae_dict[key], save_as_half)
del vae_dict
if save_as_half and not theta_func2:
for key in theta_0.keys():
theta_0[key] = to_half(theta_0[key], save_as_half)
if discard_weights:
regex = re.compile(discard_weights)
for key in list(theta_0):
if re.search(regex, key):
theta_0.pop(key, None)
ckpt_dir = shared.cmd_opts.ckpt_dir or sd_models.model_path
filename = \
primary_model_info.model_name + '_' + str(round(1-multiplier, 2)) + '-' + \
secondary_model_info.model_name + '_' + str(round(multiplier, 2)) + '-' + \
interp_method.replace(" ", "_") + \
'-merged.' + \
("inpainting." if result_is_inpainting_model else "") + \
checkpoint_format
filename = filename if custom_name == '' else (custom_name + '.' + checkpoint_format)
filename = filename_generator() if custom_name == '' else custom_name
filename += ".inpainting" if result_is_inpainting_model else ""
filename += "." + checkpoint_format
output_modelname = os.path.join(ckpt_dir, filename)
shared.state.textinfo = f"Saving to {output_modelname}..."
shared.state.nextjob()
shared.state.textinfo = "Saving"
print(f"Saving to {output_modelname}...")
_, extension = os.path.splitext(output_modelname)
@ -384,8 +459,8 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
create_config(output_modelname, config_source, primary_model_info, secondary_model_info, tertiary_model_info)
print("Checkpoint saved.")
shared.state.textinfo = "Checkpoint saved to " + output_modelname
print(f"Checkpoint saved to {output_modelname}.")
shared.state.textinfo = "Checkpoint saved"
shared.state.end()
return ["Checkpoint saved to " + output_modelname] + [gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)]
return [*[gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)], "Checkpoint saved to " + output_modelname]

15
modules/generation_parameters_copypaste.py
View File

@ -37,6 +37,9 @@ def quote(text):
def image_from_url_text(filedata):
if filedata is None:
return None
if type(filedata) == list and len(filedata) > 0 and type(filedata[0]) == dict and filedata[0].get("is_file", False):
filedata = filedata[0]
@ -76,8 +79,6 @@ def integrate_settings_paste_fields(component_dict):
from modules import ui
settings_map = {
'sd_hypernetwork': 'Hypernet',
'sd_hypernetwork_strength': 'Hypernet strength',
'CLIP_stop_at_last_layers': 'Clip skip',
'inpainting_mask_weight': 'Conditional mask weight',
'sd_model_checkpoint': 'Model hash',
@ -272,13 +273,9 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
if "Clip skip" not in res:
res["Clip skip"] = "1"
if "Hypernet strength" not in res:
res["Hypernet strength"] = "1"
if "Hypernet" in res:
hypernet_name = res["Hypernet"]
hypernet_hash = res.get("Hypernet hash", None)
res["Hypernet"] = find_hypernetwork_key(hypernet_name, hypernet_hash)
hypernet = res.get("Hypernet", None)
if hypernet is not None:
res["Prompt"] += f"""<hypernet:{hypernet}:{res.get("Hypernet strength", "1.0")}>"""
if "Hires resize-1" not in res:
res["Hires resize-1"] = 0

3
modules/hashes.py
View File

@ -34,9 +34,10 @@ def cache(subsection):
def calculate_sha256(filename):
hash_sha256 = hashlib.sha256()
blksize = 1024 * 1024
with open(filename, "rb") as f:
for chunk in iter(lambda: f.read(4096), b""):
for chunk in iter(lambda: f.read(blksize), b""):
hash_sha256.update(chunk)
return hash_sha256.hexdigest()

133
modules/hypernetworks/hypernetwork.py
View File

@ -12,7 +12,7 @@ import torch
import tqdm
from einops import rearrange, repeat
from ldm.util import default
from modules import devices, processing, sd_models, shared, sd_samplers, hashes
from modules import devices, processing, sd_models, shared, sd_samplers, hashes, sd_hijack_checkpoint
from modules.textual_inversion import textual_inversion, logging
from modules.textual_inversion.learn_schedule import LearnRateScheduler
from torch import einsum
@ -25,7 +25,6 @@ from statistics import stdev, mean
optimizer_dict = {optim_name : cls_obj for optim_name, cls_obj in inspect.getmembers(torch.optim, inspect.isclass) if optim_name != "Optimizer"}
class HypernetworkModule(torch.nn.Module):
multiplier = 1.0
activation_dict = {
"linear": torch.nn.Identity,
"relu": torch.nn.ReLU,
@ -41,6 +40,8 @@ class HypernetworkModule(torch.nn.Module):
add_layer_norm=False, activate_output=False, dropout_structure=None):
super().__init__()
self.multiplier = 1.0
assert layer_structure is not None, "layer_structure must not be None"
assert layer_structure[0] == 1, "Multiplier Sequence should start with size 1!"
assert layer_structure[-1] == 1, "Multiplier Sequence should end with size 1!"
@ -115,7 +116,7 @@ class HypernetworkModule(torch.nn.Module):
state_dict[to] = x
def forward(self, x):
return x + self.linear(x) * (HypernetworkModule.multiplier if not self.training else 1)
return x + self.linear(x) * (self.multiplier if not self.training else 1)
def trainables(self):
layer_structure = []
@ -125,9 +126,6 @@ class HypernetworkModule(torch.nn.Module):
return layer_structure
def apply_strength(value=None):
HypernetworkModule.multiplier = value if value is not None else shared.opts.sd_hypernetwork_strength
#param layer_structure : sequence used for length, use_dropout : controlling boolean, last_layer_dropout : for compatibility check.
def parse_dropout_structure(layer_structure, use_dropout, last_layer_dropout):
if layer_structure is None:
@ -192,6 +190,20 @@ class Hypernetwork:
for param in layer.parameters():
param.requires_grad = mode
def to(self, device):
for k, layers in self.layers.items():
for layer in layers:
layer.to(device)
return self
def set_multiplier(self, multiplier):
for k, layers in self.layers.items():
for layer in layers:
layer.multiplier = multiplier
return self
def eval(self):
for k, layers in self.layers.items():
for layer in layers:
@ -269,11 +281,13 @@ class Hypernetwork:
self.optimizer_state_dict = None
if self.optimizer_state_dict:
self.optimizer_name = optimizer_saved_dict.get('optimizer_name', 'AdamW')
print("Loaded existing optimizer from checkpoint")
print(f"Optimizer name is {self.optimizer_name}")
if shared.opts.print_hypernet_extra:
print("Loaded existing optimizer from checkpoint")
print(f"Optimizer name is {self.optimizer_name}")
else:
self.optimizer_name = "AdamW"
print("No saved optimizer exists in checkpoint")
if shared.opts.print_hypernet_extra:
print("No saved optimizer exists in checkpoint")
for size, sd in state_dict.items():
if type(size) == int:
@ -306,23 +320,43 @@ def list_hypernetworks(path):
return res
def load_hypernetwork(filename):
path = shared.hypernetworks.get(filename, None)
# Prevent any file named "None.pt" from being loaded.
if path is not None and filename != "None":
print(f"Loading hypernetwork {filename}")
try:
shared.loaded_hypernetwork = Hypernetwork()
shared.loaded_hypernetwork.load(path)
def load_hypernetwork(name):
path = shared.hypernetworks.get(name, None)
except Exception:
print(f"Error loading hypernetwork {path}", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
else:
if shared.loaded_hypernetwork is not None:
print("Unloading hypernetwork")
if path is None:
return None
shared.loaded_hypernetwork = None
hypernetwork = Hypernetwork()
try:
hypernetwork.load(path)
except Exception:
print(f"Error loading hypernetwork {path}", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
return None
return hypernetwork
def load_hypernetworks(names, multipliers=None):
already_loaded = {}
for hypernetwork in shared.loaded_hypernetworks:
if hypernetwork.name in names:
already_loaded[hypernetwork.name] = hypernetwork
shared.loaded_hypernetworks.clear()
for i, name in enumerate(names):
hypernetwork = already_loaded.get(name, None)
if hypernetwork is None:
hypernetwork = load_hypernetwork(name)
if hypernetwork is None:
continue
hypernetwork.set_multiplier(multipliers[i] if multipliers else 1.0)
shared.loaded_hypernetworks.append(hypernetwork)
def find_closest_hypernetwork_name(search: str):
@ -336,18 +370,27 @@ def find_closest_hypernetwork_name(search: str):
return applicable[0]
def apply_hypernetwork(hypernetwork, context, layer=None):
hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
def apply_single_hypernetwork(hypernetwork, context_k, context_v, layer=None):
hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context_k.shape[2], None)
if hypernetwork_layers is None:
return context, context
return context_k, context_v
if layer is not None:
layer.hyper_k = hypernetwork_layers[0]
layer.hyper_v = hypernetwork_layers[1]
context_k = hypernetwork_layers[0](context)
context_v = hypernetwork_layers[1](context)
context_k = hypernetwork_layers[0](context_k)
context_v = hypernetwork_layers[1](context_v)
return context_k, context_v
def apply_hypernetworks(hypernetworks, context, layer=None):
context_k = context
context_v = context
for hypernetwork in hypernetworks:
context_k, context_v = apply_single_hypernetwork(hypernetwork, context_k, context_v, layer)
return context_k, context_v
@ -357,7 +400,7 @@ def attention_CrossAttention_forward(self, x, context=None, mask=None):
q = self.to_q(x)
context = default(context, x)
context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context, self)
context_k, context_v = apply_hypernetworks(shared.loaded_hypernetworks, context, self)
k = self.to_k(context_k)
v = self.to_v(context_v)
@ -453,7 +496,7 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None,
shared.reload_hypernetworks()
def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_filename, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_filename, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
# images allows training previews to have infotext. Importing it at the top causes a circular import problem.
from modules import images
@ -464,8 +507,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
template_file = template_file.path
path = shared.hypernetworks.get(hypernetwork_name, None)
shared.loaded_hypernetwork = Hypernetwork()
shared.loaded_hypernetwork.load(path)
hypernetwork = Hypernetwork()
hypernetwork.load(path)
shared.loaded_hypernetworks = [hypernetwork]
shared.state.job = "train-hypernetwork"
shared.state.textinfo = "Initializing hypernetwork training..."
@ -489,7 +533,6 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
else:
images_dir = None
hypernetwork = shared.loaded_hypernetwork
checkpoint = sd_models.select_checkpoint()
initial_step = hypernetwork.step or 0
@ -561,6 +604,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
_loss_step = 0 #internal
# size = len(ds.indexes)
# loss_dict = defaultdict(lambda : deque(maxlen = 1024))
loss_logging = deque(maxlen=len(ds) * 3) # this should be configurable parameter, this is 3 * epoch(dataset size)
# losses = torch.zeros((size,))
# previous_mean_losses = [0]
# previous_mean_loss = 0
@ -574,6 +618,8 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
pbar = tqdm.tqdm(total=steps - initial_step)
try:
sd_hijack_checkpoint.add()
for i in range((steps-initial_step) * gradient_step):
if scheduler.finished:
break
@ -610,7 +656,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
# go back until we reach gradient accumulation steps
if (j + 1) % gradient_step != 0:
continue
loss_logging.append(_loss_step)
if clip_grad:
clip_grad(weights, clip_grad_sched.learn_rate)
@ -629,7 +675,6 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
description = f"Training hypernetwork [Epoch {epoch_num}: {epoch_step+1}/{steps_per_epoch}]loss: {loss_step:.7f}"
pbar.set_description(description)
shared.state.textinfo = description
if hypernetwork_dir is not None and steps_done % save_hypernetwork_every == 0:
# Before saving, change name to match current checkpoint.
hypernetwork_name_every = f'{hypernetwork_name}-{steps_done}'
@ -645,7 +690,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
if shared.opts.training_enable_tensorboard:
epoch_num = hypernetwork.step // len(ds)
epoch_step = hypernetwork.step - (epoch_num * len(ds)) + 1
mean_loss = sum(loss_logging) / len(loss_logging)
textual_inversion.tensorboard_add(tensorboard_writer, loss=mean_loss, global_step=hypernetwork.step, step=epoch_step, learn_rate=scheduler.learn_rate, epoch_num=epoch_num)
textual_inversion.write_loss(log_directory, "hypernetwork_loss.csv", hypernetwork.step, steps_per_epoch, {
@ -670,6 +715,8 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
do_not_save_samples=True,
)
p.disable_extra_networks = True
if preview_from_txt2img:
p.prompt = preview_prompt
p.negative_prompt = preview_negative_prompt
@ -689,9 +736,6 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
processed = processing.process_images(p)
image = processed.images[0] if len(processed.images) > 0 else None
if shared.opts.training_enable_tensorboard and shared.opts.training_tensorboard_save_images:
textual_inversion.tensorboard_add_image(tensorboard_writer, f"Validation at epoch {epoch_num}", image, hypernetwork.step)
if unload:
shared.sd_model.cond_stage_model.to(devices.cpu)
@ -701,7 +745,11 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
torch.cuda.set_rng_state_all(cuda_rng_state)
hypernetwork.train()
if image is not None:
shared.state.current_image = image
shared.state.assign_current_image(image)
if shared.opts.training_enable_tensorboard and shared.opts.training_tensorboard_save_images:
textual_inversion.tensorboard_add_image(tensorboard_writer,
f"Validation at epoch {epoch_num}", image,
hypernetwork.step)
last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename, save_to_dirs=False)
last_saved_image += f", prompt: {preview_text}"
@ -723,6 +771,9 @@ Last saved image: {html.escape(last_saved_image)}<br/>
pbar.close()
hypernetwork.eval()
#report_statistics(loss_dict)
sd_hijack_checkpoint.remove()
filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt')
hypernetwork.optimizer_name = optimizer_name

5
modules/hypernetworks/ui.py
View File

@ -9,6 +9,7 @@ from modules import devices, sd_hijack, shared
not_available = ["hardswish", "multiheadattention"]
keys = list(x for x in modules.hypernetworks.hypernetwork.HypernetworkModule.activation_dict.keys() if x not in not_available)
def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False, dropout_structure=None):
filename = modules.hypernetworks.hypernetwork.create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure, activation_func, weight_init, add_layer_norm, use_dropout, dropout_structure)
@ -16,8 +17,7 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None,
def train_hypernetwork(*args):
initial_hypernetwork = shared.loaded_hypernetwork
shared.loaded_hypernetworks = []
assert not shared.cmd_opts.lowvram, 'Training models with lowvram is not possible'
@ -34,7 +34,6 @@ Hypernetwork saved to {html.escape(filename)}
except Exception:
raise
finally:
shared.loaded_hypernetwork = initial_hypernetwork
shared.sd_model.cond_stage_model.to(devices.device)
shared.sd_model.first_stage_model.to(devices.device)
sd_hijack.apply_optimizations()

5
modules/images.py
View File

@ -605,8 +605,9 @@ def read_info_from_image(image):
except ValueError:
exif_comment = exif_comment.decode('utf8', errors="ignore")
items['exif comment'] = exif_comment
geninfo = exif_comment
if exif_comment:
items['exif comment'] = exif_comment
geninfo = exif_comment
for field in ['jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif',
'loop', 'background', 'timestamp', 'duration']:

4
modules/img2img.py
View File

@ -59,7 +59,7 @@ def process_batch(p, input_dir, output_dir, args):
processed_image.save(os.path.join(output_dir, filename))
def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, *args):
def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, *args):
is_batch = mode == 5
if mode == 0: # img2img
@ -101,7 +101,7 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
outpath_grids=opts.outdir_grids or opts.outdir_img2img_grids,
prompt=prompt,
negative_prompt=negative_prompt,
styles=[prompt_style, prompt_style2],
styles=prompt_styles,
seed=seed,
subseed=subseed,
subseed_strength=subseed_strength,

55
modules/interrogate.py
View File

@ -5,12 +5,13 @@ from collections import namedtuple
import re
import torch
import torch.hub
from torchvision import transforms
from torchvision.transforms.functional import InterpolationMode
import modules.shared as shared
from modules import devices, paths, lowvram, modelloader
from modules import devices, paths, lowvram, modelloader, errors
blip_image_eval_size = 384
clip_model_name = 'ViT-L/14'
@ -20,27 +21,59 @@ Category = namedtuple("Category", ["name", "topn", "items"])
re_topn = re.compile(r"\.top(\d+)\.")
def download_default_clip_interrogate_categories(content_dir):
print("Downloading CLIP categories...")
tmpdir = content_dir + "_tmp"
try:
os.makedirs(tmpdir)
torch.hub.download_url_to_file("https://raw.githubusercontent.com/pharmapsychotic/clip-interrogator/main/clip_interrogator/data/artists.txt", os.path.join(tmpdir, "artists.txt"))
torch.hub.download_url_to_file("https://raw.githubusercontent.com/pharmapsychotic/clip-interrogator/main/clip_interrogator/data/flavors.txt", os.path.join(tmpdir, "flavors.top3.txt"))
torch.hub.download_url_to_file("https://raw.githubusercontent.com/pharmapsychotic/clip-interrogator/main/clip_interrogator/data/mediums.txt", os.path.join(tmpdir, "mediums.txt"))
torch.hub.download_url_to_file("https://raw.githubusercontent.com/pharmapsychotic/clip-interrogator/main/clip_interrogator/data/movements.txt", os.path.join(tmpdir, "movements.txt"))
os.rename(tmpdir, content_dir)
except Exception as e:
errors.display(e, "downloading default CLIP interrogate categories")
finally:
if os.path.exists(tmpdir):
os.remove(tmpdir)
class InterrogateModels:
blip_model = None
clip_model = None
clip_preprocess = None
categories = None
dtype = None
running_on_cpu = None
def __init__(self, content_dir):
self.categories = []
self.loaded_categories = None
self.content_dir = content_dir
self.running_on_cpu = devices.device_interrogate == torch.device("cpu")
if os.path.exists(content_dir):
for filename in os.listdir(content_dir):
def categories(self):
if self.loaded_categories is not None:
return self.loaded_categories
self.loaded_categories = []
if not os.path.exists(self.content_dir):
download_default_clip_interrogate_categories(self.content_dir)
if os.path.exists(self.content_dir):
for filename in os.listdir(self.content_dir):
m = re_topn.search(filename)
topn = 1 if m is None else int(m.group(1))
with open(os.path.join(content_dir, filename), "r", encoding="utf8") as file:
with open(os.path.join(self.content_dir, filename), "r", encoding="utf8") as file:
lines = [x.strip() for x in file.readlines()]
self.categories.append(Category(name=filename, topn=topn, items=lines))
self.loaded_categories.append(Category(name=filename, topn=topn, items=lines))
return self.loaded_categories
def load_blip_model(self):
import models.blip
@ -139,7 +172,6 @@ class InterrogateModels:
shared.state.begin()
shared.state.job = 'interrogate'
try:
if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
lowvram.send_everything_to_cpu()
devices.torch_gc()
@ -159,12 +191,7 @@ class InterrogateModels:
image_features /= image_features.norm(dim=-1, keepdim=True)
if shared.opts.interrogate_use_builtin_artists:
artist = self.rank(image_features, ["by " + artist.name for artist in shared.artist_db.artists])[0]
res += ", " + artist[0]
for name, topn, items in self.categories:
for name, topn, items in self.categories():
matches = self.rank(image_features, items, top_count=topn)
for match, score in matches:
if shared.opts.interrogate_return_ranks:

53
modules/processing.py
View File

@ -13,7 +13,7 @@ from skimage import exposure
from typing import Any, Dict, List, Optional
import modules.sd_hijack
from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, script_callbacks
from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, script_callbacks, extra_networks
from modules.sd_hijack import model_hijack
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
@ -94,7 +94,7 @@ def txt2img_image_conditioning(sd_model, x, width, height):
return image_conditioning
class StableDiffusionProcessing():
class StableDiffusionProcessing:
"""
The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
"""
@ -102,7 +102,6 @@ class StableDiffusionProcessing():
if sampler_index is not None:
print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
self.sd_model = sd_model
self.outpath_samples: str = outpath_samples
self.outpath_grids: str = outpath_grids
self.prompt: str = prompt
@ -141,6 +140,7 @@ class StableDiffusionProcessing():
self.override_settings = {k: v for k, v in (override_settings or {}).items() if k not in shared.restricted_opts}
self.override_settings_restore_afterwards = override_settings_restore_afterwards
self.is_using_inpainting_conditioning = False
self.disable_extra_networks = False
if not seed_enable_extras:
self.subseed = -1
@ -156,6 +156,10 @@ class StableDiffusionProcessing():
self.all_subseeds = None
self.iteration = 0
@property
def sd_model(self):
return shared.sd_model
def txt2img_image_conditioning(self, x, width=None, height=None):
self.is_using_inpainting_conditioning = self.sd_model.model.conditioning_key in {'hybrid', 'concat'}
@ -236,7 +240,6 @@ class StableDiffusionProcessing():
raise NotImplementedError()
def close(self):
self.sd_model = None
self.sampler = None
@ -436,9 +439,6 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
"Size": f"{p.width}x{p.height}",
"Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
"Model": (None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', '')),
"Hypernet": (None if shared.loaded_hypernetwork is None else shared.loaded_hypernetwork.name),
"Hypernet hash": (None if shared.loaded_hypernetwork is None else shared.loaded_hypernetwork.shorthash()),
"Hypernet strength": (None if shared.loaded_hypernetwork is None or shared.opts.sd_hypernetwork_strength >= 1 else shared.opts.sd_hypernetwork_strength),
"Batch size": (None if p.batch_size < 2 else p.batch_size),
"Batch pos": (None if p.batch_size < 2 else position_in_batch),
"Variation seed": (None if p.subseed_strength == 0 else all_subseeds[index]),
@ -466,15 +466,12 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
try:
for k, v in p.override_settings.items():
setattr(opts, k, v)
if k == 'sd_hypernetwork':
shared.reload_hypernetworks() # make onchange call for changing hypernet
if k == 'sd_model_checkpoint':
sd_models.reload_model_weights() # make onchange call for changing SD model
p.sd_model = shared.sd_model
sd_models.reload_model_weights()
if k == 'sd_vae':
sd_vae.reload_vae_weights() # make onchange call for changing VAE
sd_vae.reload_vae_weights()
res = process_images_inner(p)
@ -483,9 +480,11 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
if p.override_settings_restore_afterwards:
for k, v in stored_opts.items():
setattr(opts, k, v)
if k == 'sd_hypernetwork': shared.reload_hypernetworks()
if k == 'sd_model_checkpoint': sd_models.reload_model_weights()
if k == 'sd_vae': sd_vae.reload_vae_weights()
if k == 'sd_model_checkpoint':
sd_models.reload_model_weights()
if k == 'sd_vae':
sd_vae.reload_vae_weights()
return res
@ -534,13 +533,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
if os.path.exists(cmd_opts.embeddings_dir) and not p.do_not_reload_embeddings:
model_hijack.embedding_db.load_textual_inversion_embeddings()
_, extra_network_data = extra_networks.parse_prompts(p.all_prompts[0:1])
if p.scripts is not None:
p.scripts.process(p)
with open(os.path.join(shared.script_path, "params.txt"), "w", encoding="utf8") as file:
processed = Processed(p, [], p.seed, "")
file.write(processed.infotext(p, 0))
infotexts = []
output_images = []
@ -571,6 +568,13 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
with devices.autocast():
p.init(p.all_prompts, p.all_seeds, p.all_subseeds)
if not p.disable_extra_networks:
extra_networks.activate(p, extra_network_data)
with open(os.path.join(shared.script_path, "params.txt"), "w", encoding="utf8") as file:
processed = Processed(p, [], p.seed, "")
file.write(processed.infotext(p, 0))
if state.job_count == -1:
state.job_count = p.n_iter
@ -591,6 +595,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
if len(prompts) == 0:
break
prompts, _ = extra_networks.parse_prompts(prompts)
if p.scripts is not None:
p.scripts.process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds)
@ -608,6 +614,9 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
for x in x_samples_ddim:
devices.test_for_nans(x, "vae")
x_samples_ddim = torch.stack(x_samples_ddim).float()
x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
@ -677,6 +686,9 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
if opts.grid_save:
images.save_image(grid, p.outpath_grids, "grid", p.all_seeds[0], p.all_prompts[0], opts.grid_format, info=infotext(), short_filename=not opts.grid_extended_filename, p=p, grid=True)
if not p.disable_extra_networks:
extra_networks.deactivate(p, extra_network_data)
devices.torch_gc()
res = Processed(p, output_images, p.all_seeds[0], infotext(), comments="".join(["\n\n" + x for x in comments]), subseed=p.all_subseeds[0], index_of_first_image=index_of_first_image, infotexts=infotexts)
@ -853,7 +865,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
shared.state.nextjob()
self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
img2img_sampler_name = self.sampler_name if self.sampler_name != 'PLMS' else 'DDIM' # PLMS does not support img2img so we just silently switch ot DDIM
self.sampler = sd_samplers.create_sampler(img2img_sampler_name, self.sd_model)
samples = samples[:, :, self.truncate_y//2:samples.shape[2]-(self.truncate_y+1)//2, self.truncate_x//2:samples.shape[3]-(self.truncate_x+1)//2]

99
modules/progress.py Normal file
View File

@ -0,0 +1,99 @@
import base64
import io
import time
import gradio as gr
from pydantic import BaseModel, Field
from modules.shared import opts
import modules.shared as shared
current_task = None
pending_tasks = {}
finished_tasks = []
def start_task(id_task):
global current_task
current_task = id_task
pending_tasks.pop(id_task, None)
def finish_task(id_task):
global current_task
if current_task == id_task:
current_task = None
finished_tasks.append(id_task)
if len(finished_tasks) > 16:
finished_tasks.pop(0)
def add_task_to_queue(id_job):
pending_tasks[id_job] = time.time()
class ProgressRequest(BaseModel):
id_task: str = Field(default=None, title="Task ID", description="id of the task to get progress for")
id_live_preview: int = Field(default=-1, title="Live preview image ID", description="id of last received last preview image")
class ProgressResponse(BaseModel):
active: bool = Field(title="Whether the task is being worked on right now")
queued: bool = Field(title="Whether the task is in queue")
completed: bool = Field(title="Whether the task has already finished")
progress: float = Field(default=None, title="Progress", description="The progress with a range of 0 to 1")
eta: float = Field(default=None, title="ETA in secs")
live_preview: str = Field(default=None, title="Live preview image", description="Current live preview; a data: uri")
id_live_preview: int = Field(default=None, title="Live preview image ID", description="Send this together with next request to prevent receiving same image")
textinfo: str = Field(default=None, title="Info text", description="Info text used by WebUI.")
def setup_progress_api(app):
return app.add_api_route("/internal/progress", progressapi, methods=["POST"], response_model=ProgressResponse)
def progressapi(req: ProgressRequest):
active = req.id_task == current_task
queued = req.id_task in pending_tasks
completed = req.id_task in finished_tasks
if not active:
return ProgressResponse(active=active, queued=queued, completed=completed, id_live_preview=-1, textinfo="In queue..." if queued else "Waiting...")
progress = 0
job_count, job_no = shared.state.job_count, shared.state.job_no
sampling_steps, sampling_step = shared.state.sampling_steps, shared.state.sampling_step
if job_count > 0:
progress += job_no / job_count
if sampling_steps > 0 and job_count > 0:
progress += 1 / job_count * sampling_step / sampling_steps
progress = min(progress, 1)
elapsed_since_start = time.time() - shared.state.time_start
predicted_duration = elapsed_since_start / progress if progress > 0 else None
eta = predicted_duration - elapsed_since_start if predicted_duration is not None else None
id_live_preview = req.id_live_preview
shared.state.set_current_image()
if opts.live_previews_enable and shared.state.id_live_preview != req.id_live_preview:
image = shared.state.current_image
if image is not None:
buffered = io.BytesIO()
image.save(buffered, format="png")
live_preview = 'data:image/png;base64,' + base64.b64encode(buffered.getvalue()).decode("ascii")
id_live_preview = shared.state.id_live_preview
else:
live_preview = None
else:
live_preview = None
return ProgressResponse(active=active, queued=queued, completed=completed, progress=progress, eta=eta, live_preview=live_preview, id_live_preview=id_live_preview, textinfo=shared.state.textinfo)

7
modules/prompt_parser.py
View File

@ -274,6 +274,7 @@ re_attention = re.compile(r"""
:
""", re.X)
re_break = re.compile(r"\s*\bBREAK\b\s*", re.S)
def parse_prompt_attention(text):
"""
@ -339,7 +340,11 @@ def parse_prompt_attention(text):
elif text == ']' and len(square_brackets) > 0:
multiply_range(square_brackets.pop(), square_bracket_multiplier)
else:
res.append([text, 1.0])
parts = re.split(re_break, text)
for i, part in enumerate(parts):
if i > 0:
res.append(["BREAK", -1])
res.append([part, 1.0])
for pos in round_brackets:
multiply_range(pos, round_bracket_multiplier)

12
modules/realesrgan_model.py
View File

@ -38,13 +38,13 @@ class UpscalerRealESRGAN(Upscaler):
return img
info = self.load_model(path)
if not os.path.exists(info.data_path):
if not os.path.exists(info.local_data_path):
print("Unable to load RealESRGAN model: %s" % info.name)
return img
upsampler = RealESRGANer(
scale=info.scale,
model_path=info.data_path,
model_path=info.local_data_path,
model=info.model(),
half=not cmd_opts.no_half,
tile=opts.ESRGAN_tile,
@ -58,17 +58,13 @@ class UpscalerRealESRGAN(Upscaler):
def load_model(self, path):
try:
info = None
for scaler in self.scalers:
if scaler.data_path == path:
info = scaler
info = next(iter([scaler for scaler in self.scalers if scaler.data_path == path]), None)
if info is None:
print(f"Unable to find model info: {path}")
return None
model_file = load_file_from_url(url=info.data_path, model_dir=self.model_path, progress=True)
info.data_path = model_file
info.local_data_path = load_file_from_url(url=info.data_path, model_dir=self.model_path, progress=True)
return info
except Exception as e:
print(f"Error making Real-ESRGAN models list: {e}", file=sys.stderr)

15
modules/script_callbacks.py
View File

@ -73,6 +73,7 @@ callback_map = dict(
callbacks_image_grid=[],
callbacks_infotext_pasted=[],
callbacks_script_unloaded=[],
callbacks_before_ui=[],
)
@ -189,6 +190,14 @@ def script_unloaded_callback():
report_exception(c, 'script_unloaded')
def before_ui_callback():
for c in reversed(callback_map['callbacks_before_ui']):
try:
c.callback()
except Exception:
report_exception(c, 'before_ui')
def add_callback(callbacks, fun):
stack = [x for x in inspect.stack() if x.filename != __file__]
filename = stack[0].filename if len(stack) > 0 else 'unknown file'
@ -313,3 +322,9 @@ def on_script_unloaded(callback):
the script did should be reverted here"""
add_callback(callback_map['callbacks_script_unloaded'], callback)
def on_before_ui(callback):
"""register a function to be called before the UI is created."""
add_callback(callback_map['callbacks_before_ui'], callback)

4
modules/sd_disable_initialization.py
View File

@ -41,7 +41,9 @@ class DisableInitialization:
return self.create_model_and_transforms(*args, pretrained=None, **kwargs)
def CLIPTextModel_from_pretrained(pretrained_model_name_or_path, *model_args, **kwargs):
return self.CLIPTextModel_from_pretrained(None, *model_args, config=pretrained_model_name_or_path, state_dict={}, **kwargs)
res = self.CLIPTextModel_from_pretrained(None, *model_args, config=pretrained_model_name_or_path, state_dict={}, **kwargs)
res.name_or_path = pretrained_model_name_or_path
return res
def transformers_modeling_utils_load_pretrained_model(*args, **kwargs):
args = args[0:3] + ('/', ) + args[4:] # resolved_archive_file; must set it to something to prevent what seems to be a bug

9
modules/sd_hijack.py
View File

@ -70,9 +70,10 @@ def undo_optimizations():
def fix_checkpoint():
ldm.modules.attention.BasicTransformerBlock.forward = sd_hijack_checkpoint.BasicTransformerBlock_forward
ldm.modules.diffusionmodules.openaimodel.ResBlock.forward = sd_hijack_checkpoint.ResBlock_forward
ldm.modules.diffusionmodules.openaimodel.AttentionBlock.forward = sd_hijack_checkpoint.AttentionBlock_forward
"""checkpoints are now added and removed in embedding/hypernet code, since torch doesn't want
checkpoints to be added when not training (there's a warning)"""
pass
class StableDiffusionModelHijack:
@ -106,8 +107,6 @@ class StableDiffusionModelHijack:
self.optimization_method = apply_optimizations()
self.clip = m.cond_stage_model
fix_checkpoint()
def flatten(el):
flattened = [flatten(children) for children in el.children()]

38
modules/sd_hijack_checkpoint.py
View File

@ -1,10 +1,46 @@
from torch.utils.checkpoint import checkpoint
import ldm.modules.attention
import ldm.modules.diffusionmodules.openaimodel
def BasicTransformerBlock_forward(self, x, context=None):
return checkpoint(self._forward, x, context)
def AttentionBlock_forward(self, x):
return checkpoint(self._forward, x)
def ResBlock_forward(self, x, emb):
return checkpoint(self._forward, x, emb)
return checkpoint(self._forward, x, emb)
stored = []
def add():
if len(stored) != 0:
return
stored.extend([
ldm.modules.attention.BasicTransformerBlock.forward,
ldm.modules.diffusionmodules.openaimodel.ResBlock.forward,
ldm.modules.diffusionmodules.openaimodel.AttentionBlock.forward
])
ldm.modules.attention.BasicTransformerBlock.forward = BasicTransformerBlock_forward
ldm.modules.diffusionmodules.openaimodel.ResBlock.forward = ResBlock_forward
ldm.modules.diffusionmodules.openaimodel.AttentionBlock.forward = AttentionBlock_forward
def remove():
if len(stored) == 0:
return
ldm.modules.attention.BasicTransformerBlock.forward = stored[0]
ldm.modules.diffusionmodules.openaimodel.ResBlock.forward = stored[1]
ldm.modules.diffusionmodules.openaimodel.AttentionBlock.forward = stored[2]
stored.clear()

17
modules/sd_hijack_clip.py
View File

@ -96,13 +96,18 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
token_count = 0
last_comma = -1
def next_chunk():
"""puts current chunk into the list of results and produces the next one - empty"""
def next_chunk(is_last=False):
"""puts current chunk into the list of results and produces the next one - empty;
if is_last is true, tokens <end-of-text> tokens at the end won't add to token_count"""
nonlocal token_count
nonlocal last_comma
nonlocal chunk
token_count += len(chunk.tokens)
if is_last:
token_count += len(chunk.tokens)
else:
token_count += self.chunk_length
to_add = self.chunk_length - len(chunk.tokens)
if to_add > 0:
chunk.tokens += [self.id_end] * to_add
@ -116,6 +121,10 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
chunk = PromptChunk()
for tokens, (text, weight) in zip(tokenized, parsed):
if text == 'BREAK' and weight == -1:
next_chunk()
continue
position = 0
while position < len(tokens):
token = tokens[position]
@ -159,7 +168,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
position += embedding_length_in_tokens
if len(chunk.tokens) > 0 or len(chunks) == 0:
next_chunk()
next_chunk(is_last=True)
return chunks, token_count

10
modules/sd_hijack_optimizations.py
View File

@ -44,7 +44,7 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None):
q_in = self.to_q(x)
context = default(context, x)
context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
context_k, context_v = hypernetwork.apply_hypernetworks(shared.loaded_hypernetworks, context)
k_in = self.to_k(context_k)
v_in = self.to_v(context_v)
del context, context_k, context_v, x
@ -78,7 +78,7 @@ def split_cross_attention_forward(self, x, context=None, mask=None):
q_in = self.to_q(x)
context = default(context, x)
context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
context_k, context_v = hypernetwork.apply_hypernetworks(shared.loaded_hypernetworks, context)
k_in = self.to_k(context_k)
v_in = self.to_v(context_v)
@ -203,7 +203,7 @@ def split_cross_attention_forward_invokeAI(self, x, context=None, mask=None):
q = self.to_q(x)
context = default(context, x)
context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
context_k, context_v = hypernetwork.apply_hypernetworks(shared.loaded_hypernetworks, context)
k = self.to_k(context_k) * self.scale
v = self.to_v(context_v)
del context, context_k, context_v, x
@ -225,7 +225,7 @@ def sub_quad_attention_forward(self, x, context=None, mask=None):
q = self.to_q(x)
context = default(context, x)
context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
context_k, context_v = hypernetwork.apply_hypernetworks(shared.loaded_hypernetworks, context)
k = self.to_k(context_k)
v = self.to_v(context_v)
del context, context_k, context_v, x
@ -284,7 +284,7 @@ def xformers_attention_forward(self, x, context=None, mask=None):
q_in = self.to_q(x)
context = default(context, x)
context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
context_k, context_v = hypernetwork.apply_hypernetworks(shared.loaded_hypernetworks, context)
k_in = self.to_k(context_k)
v_in = self.to_v(context_v)

15
modules/sd_models.py
View File

@ -41,14 +41,16 @@ class CheckpointInfo:
if name.startswith("\\") or name.startswith("/"):
name = name[1:]
self.title = name
self.name = name
self.model_name = os.path.splitext(name.replace("/", "_").replace("\\", "_"))[0]
self.hash = model_hash(filename)
self.sha256 = hashes.sha256_from_cache(self.filename, "checkpoint/" + self.title)
self.sha256 = hashes.sha256_from_cache(self.filename, "checkpoint/" + name)
self.shorthash = self.sha256[0:10] if self.sha256 else None
self.ids = [self.hash, self.model_name, self.title, f'{name} [{self.hash}]'] + ([self.shorthash, self.sha256] if self.shorthash else [])
self.title = name if self.shorthash is None else f'{name} [{self.shorthash}]'
self.ids = [self.hash, self.model_name, self.title, name, f'{name} [{self.hash}]'] + ([self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]'] if self.shorthash else [])
def register(self):
checkpoints_list[self.title] = self
@ -56,13 +58,15 @@ class CheckpointInfo:
checkpoint_alisases[id] = self
def calculate_shorthash(self):
self.sha256 = hashes.sha256(self.filename, "checkpoint/" + self.title)
self.sha256 = hashes.sha256(self.filename, "checkpoint/" + self.name)
self.shorthash = self.sha256[0:10]
if self.shorthash not in self.ids:
self.ids += [self.shorthash, self.sha256]
self.register()
self.title = f'{self.name} [{self.shorthash}]'
return self.shorthash
@ -225,7 +229,10 @@ def read_state_dict(checkpoint_file, print_global_state=False, map_location=None
def load_model_weights(model, checkpoint_info: CheckpointInfo):
title = checkpoint_info.title
sd_model_hash = checkpoint_info.calculate_shorthash()
if checkpoint_info.title != title:
shared.opts.data["sd_model_checkpoint"] = checkpoint_info.title
cache_enabled = shared.opts.sd_checkpoint_cache > 0

4
modules/sd_samplers.py
View File

@ -140,7 +140,7 @@ def store_latent(decoded):
if opts.live_previews_enable and opts.show_progress_every_n_steps > 0 and shared.state.sampling_step % opts.show_progress_every_n_steps == 0:
if not shared.parallel_processing_allowed:
shared.state.current_image = sample_to_image(decoded)
shared.state.assign_current_image(sample_to_image(decoded))
class InterruptedException(BaseException):
@ -351,6 +351,8 @@ class CFGDenoiser(torch.nn.Module):
x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond={"c_crossattn": [uncond], "c_concat": [image_cond_in[-uncond.shape[0]:]]})
devices.test_for_nans(x_out, "unet")
if opts.live_preview_content == "Prompt":
store_latent(x_out[0:uncond.shape[0]])
elif opts.live_preview_content == "Negative prompt":

22
modules/sd_vae.py
View File

@ -72,6 +72,13 @@ def refresh_vae_list():
os.path.join(shared.cmd_opts.ckpt_dir, '**/*.vae.safetensors'),
]
if shared.cmd_opts.vae_dir is not None and os.path.isdir(shared.cmd_opts.vae_dir):
paths += [
os.path.join(shared.cmd_opts.vae_dir, '**/*.ckpt'),
os.path.join(shared.cmd_opts.vae_dir, '**/*.pt'),
os.path.join(shared.cmd_opts.vae_dir, '**/*.safetensors'),
]
candidates = []
for path in paths:
candidates += glob.iglob(path, recursive=True)
@ -94,8 +101,10 @@ def resolve_vae(checkpoint_file):
if shared.cmd_opts.vae_path is not None:
return shared.cmd_opts.vae_path, 'from commandline argument'
is_automatic = shared.opts.sd_vae in {"Automatic", "auto"} # "auto" for people with old config
vae_near_checkpoint = find_vae_near_checkpoint(checkpoint_file)
if vae_near_checkpoint is not None and (shared.opts.sd_vae_as_default or shared.opts.sd_vae == "Automatic"):
if vae_near_checkpoint is not None and (shared.opts.sd_vae_as_default or is_automatic):
return vae_near_checkpoint, 'found near the checkpoint'
if shared.opts.sd_vae == "None":
@ -105,12 +114,18 @@ def resolve_vae(checkpoint_file):
if vae_from_options is not None:
return vae_from_options, 'specified in settings'
if shared.opts.sd_vae != "Automatic":
if not is_automatic:
print(f"Couldn't find VAE named {shared.opts.sd_vae}; using None instead")
return None, None
def load_vae_dict(filename, map_location):
vae_ckpt = sd_models.read_state_dict(filename, map_location=map_location)
vae_dict_1 = {k: v for k, v in vae_ckpt.items() if k[0:4] != "loss" and k not in vae_ignore_keys}
return vae_dict_1
def load_vae(model, vae_file=None, vae_source="from unknown source"):
global vae_dict, loaded_vae_file
# save_settings = False
@ -128,8 +143,7 @@ def load_vae(model, vae_file=None, vae_source="from unknown source"):
print(f"Loading VAE weights {vae_source}: {vae_file}")
store_base_vae(model)
vae_ckpt = sd_models.read_state_dict(vae_file, map_location=shared.weight_load_location)
vae_dict_1 = {k: v for k, v in vae_ckpt.items() if k[0:4] != "loss" and k not in vae_ignore_keys}
vae_dict_1 = load_vae_dict(vae_file, map_location=shared.weight_load_location)
_load_vae_dict(model, vae_dict_1)
if cache_enabled:

2
modules/sd_vae_approx.py
View File

@ -36,7 +36,7 @@ def model():
if sd_vae_approx_model is None:
sd_vae_approx_model = VAEApprox()
sd_vae_approx_model.load_state_dict(torch.load(os.path.join(paths.models_path, "VAE-approx", "model.pt")))
sd_vae_approx_model.load_state_dict(torch.load(os.path.join(paths.models_path, "VAE-approx", "model.pt"), map_location='cpu' if devices.device.type != 'cuda' else None))
sd_vae_approx_model.eval()
sd_vae_approx_model.to(devices.device, devices.dtype)

73
modules/shared.py
View File

@ -9,7 +9,6 @@ from PIL import Image
import gradio as gr
import tqdm
import modules.artists
import modules.interrogate
import modules.memmon
import modules.styles
@ -20,12 +19,15 @@ from modules.paths import models_path, script_path, sd_path
demo = None
sd_default_config = os.path.join(script_path, "configs/v1-inference.yaml")
sd_model_file = os.path.join(script_path, 'model.ckpt')
default_sd_model_file = sd_model_file
parser = argparse.ArgumentParser()
parser.add_argument("--config", type=str, default=os.path.join(script_path, "configs/v1-inference.yaml"), help="path to config which constructs model",)
parser.add_argument("--config", type=str, default=sd_default_config, help="path to config which constructs model",)
parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to directory with stable diffusion checkpoints")
parser.add_argument("--vae-dir", type=str, default=None, help="Path to directory with VAE files")
parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
parser.add_argument("--gfpgan-model", type=str, help="GFPGAN model file name", default=None)
parser.add_argument("--no-half", action='store_true', help="do not switch the model to 16-bit floats")
@ -64,6 +66,7 @@ parser.add_argument("--sub-quad-chunk-threshold", type=int, help="the percentage
parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
@ -97,6 +100,8 @@ parser.add_argument("--cors-allow-origins-regex", type=str, help="Allowed CORS o
parser.add_argument("--tls-keyfile", type=str, help="Partially enables TLS, requires --tls-certfile to fully function", default=None)
parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, requires --tls-keyfile to fully function", default=None)
parser.add_argument("--server-name", type=str, help="Sets hostname of server", default=None)
parser.add_argument("--gradio-queue", action='store_true', help="Uses gradio queue; experimental option; breaks restart UI button")
script_loading.preload_extensions(extensions.extensions_dir, parser)
script_loading.preload_extensions(extensions.extensions_builtin_dir, parser)
@ -116,6 +121,7 @@ restricted_opts = {
}
ui_reorder_categories = [
"inpaint",
"sampler",
"dimensions",
"cfg",
@ -141,7 +147,7 @@ config_filename = cmd_opts.ui_settings_file
os.makedirs(cmd_opts.hypernetwork_dir, exist_ok=True)
hypernetworks = {}
loaded_hypernetwork = None
loaded_hypernetworks = []
def reload_hypernetworks():
@ -149,7 +155,6 @@ def reload_hypernetworks():
global hypernetworks
hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
hypernetwork.load_hypernetwork(opts.sd_hypernetwork)
class State:
@ -165,9 +170,11 @@ class State:
current_latent = None
current_image = None
current_image_sampling_step = 0
id_live_preview = 0
textinfo = None
time_start = None
need_restart = False
server_start = None
def skip(self):
self.skipped = True
@ -206,6 +213,7 @@ class State:
self.current_latent = None
self.current_image = None
self.current_image_sampling_step = 0
self.id_live_preview = 0
self.skipped = False
self.interrupted = False
self.textinfo = None
@ -219,12 +227,12 @@ class State:
devices.torch_gc()
"""sets self.current_image from self.current_latent if enough sampling steps have been made after the last call to this"""
def set_current_image(self):
"""sets self.current_image from self.current_latent if enough sampling steps have been made after the last call to this"""
if not parallel_processing_allowed:
return
if self.sampling_step - self.current_image_sampling_step >= opts.show_progress_every_n_steps and opts.live_previews_enable:
if self.sampling_step - self.current_image_sampling_step >= opts.show_progress_every_n_steps and opts.live_previews_enable and opts.show_progress_every_n_steps != -1:
self.do_set_current_image()
def do_set_current_image(self):
@ -233,16 +241,19 @@ class State:
import modules.sd_samplers
if opts.show_progress_grid:
self.current_image = modules.sd_samplers.samples_to_image_grid(self.current_latent)
self.assign_current_image(modules.sd_samplers.samples_to_image_grid(self.current_latent))
else:
self.current_image = modules.sd_samplers.sample_to_image(self.current_latent)
self.assign_current_image(modules.sd_samplers.sample_to_image(self.current_latent))
self.current_image_sampling_step = self.sampling_step
def assign_current_image(self, image):
self.current_image = image
self.id_live_preview += 1
state = State()
artist_db = modules.artists.ArtistsDatabase(os.path.join(script_path, 'artists.csv'))
state.server_start = time.time()
styles_filename = cmd_opts.styles_file
prompt_styles = modules.styles.StyleDatabase(styles_filename)
@ -358,6 +369,7 @@ options_templates.update(options_section(('face-restoration', "Face restoration"
}))
options_templates.update(options_section(('system', "System"), {
"show_warnings": OptionInfo(False, "Show warnings in console."),
"memmon_poll_rate": OptionInfo(8, "VRAM usage polls per second during generation. Set to 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 40, "step": 1}),
"samples_log_stdout": OptionInfo(False, "Always print all generation info to standard output"),
"multiple_tqdm": OptionInfo(True, "Add a second progress bar to the console that shows progress for an entire job."),
@ -384,11 +396,9 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
"sd_checkpoint_cache": OptionInfo(0, "Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
"sd_vae_checkpoint_cache": OptionInfo(0, "VAE Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
"sd_vae": OptionInfo("Automatic", "SD VAE", gr.Dropdown, lambda: {"choices": ["Automatic", "None"] + list(sd_vae.vae_dict)}, refresh=sd_vae.refresh_vae_list),
"sd_vae_as_default": OptionInfo(False, "Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them"),
"sd_hypernetwork": OptionInfo("None", "Hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks),
"sd_hypernetwork_strength": OptionInfo(1.0, "Hypernetwork strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.001}),
"sd_vae_as_default": OptionInfo(True, "Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them"),
"inpainting_mask_weight": OptionInfo(1.0, "Inpainting conditioning mask strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
"initial_noise_multiplier": OptionInfo(1.0, "Noise multiplier for img2img", gr.Slider, {"minimum": 0.5, "maximum": 1.5, "step": 0.01 }),
"initial_noise_multiplier": OptionInfo(1.0, "Noise multiplier for img2img", gr.Slider, {"minimum": 0.5, "maximum": 1.5, "step": 0.01}),
"img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."),
"img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising)."),
"img2img_background_color": OptionInfo("#ffffff", "With img2img, fill image's transparent parts with this color.", ui_components.FormColorPicker, {}),
@ -396,8 +406,8 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
"enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"),
"enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"),
"comma_padding_backtrack": OptionInfo(20, "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1 }),
'CLIP_stop_at_last_layers': OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}),
"random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}),
"CLIP_stop_at_last_layers": OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}),
"extra_networks_default_multiplier": OptionInfo(1.0, "Multiplier for extra networks", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
}))
options_templates.update(options_section(('compatibility', "Compatibility"), {
@ -408,7 +418,6 @@ options_templates.update(options_section(('compatibility', "Compatibility"), {
options_templates.update(options_section(('interrogate', "Interrogate Options"), {
"interrogate_keep_models_in_memory": OptionInfo(False, "Interrogate: keep models in VRAM"),
"interrogate_use_builtin_artists": OptionInfo(True, "Interrogate: use artists from artists.csv"),
"interrogate_return_ranks": OptionInfo(False, "Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators)."),
"interrogate_clip_num_beams": OptionInfo(1, "Interrogate: num_beams for BLIP", gr.Slider, {"minimum": 1, "maximum": 16, "step": 1}),
"interrogate_clip_min_length": OptionInfo(24, "Interrogate: minimum description length (excluding artists, etc..)", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}),
@ -422,8 +431,6 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"),
}))
options_templates.update(options_section(('ui', "User interface"), {
"show_progressbar": OptionInfo(True, "Show progressbar"),
"show_progress_grid": OptionInfo(True, "Show previews of all images generated in a batch as a grid"),
"return_grid": OptionInfo(True, "Show grid in results for web"),
"do_not_show_images": OptionInfo(False, "Do not show any images in results for web"),
"add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"),
@ -436,17 +443,23 @@ options_templates.update(options_section(('ui', "User interface"), {
"js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
"show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
"samplers_in_dropdown": OptionInfo(True, "Use dropdown for sampler selection instead of radio group"),
"dimensions_and_batch_together": OptionInfo(True, "Show Witdth/Height and Batch sliders in same row"),
'quicksettings': OptionInfo("sd_model_checkpoint", "Quicksettings list"),
'ui_reorder': OptionInfo(", ".join(ui_reorder_categories), "txt2img/img2img UI item order"),
'localization': OptionInfo("None", "Localization (requires restart)", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)),
"dimensions_and_batch_together": OptionInfo(True, "Show Width/Height and Batch sliders in same row"),
"keyedit_precision_attention": OptionInfo(0.1, "Ctrl+up/down precision when editing (attention:1.1)", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
"keyedit_precision_extra": OptionInfo(0.05, "Ctrl+up/down precision when editing <extra networks:0.9>", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
"quicksettings": OptionInfo("sd_model_checkpoint", "Quicksettings list"),
"ui_reorder": OptionInfo(", ".join(ui_reorder_categories), "txt2img/img2img UI item order"),
"ui_extra_networks_tab_reorder": OptionInfo("", "Extra networks tab order"),
"localization": OptionInfo("None", "Localization (requires restart)", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)),
}))
options_templates.update(options_section(('ui', "Live previews"), {
"show_progressbar": OptionInfo(True, "Show progressbar"),
"live_previews_enable": OptionInfo(True, "Show live previews of the created image"),
"show_progress_grid": OptionInfo(True, "Show previews of all images generated in a batch as a grid"),
"show_progress_every_n_steps": OptionInfo(10, "Show new live preview image every N sampling steps. Set to -1 to show after completion of batch.", gr.Slider, {"minimum": -1, "maximum": 32, "step": 1}),
"show_progress_type": OptionInfo("Approx NN", "Image creation progress preview mode", gr.Radio, {"choices": ["Full", "Approx NN", "Approx cheap"]}),
"live_preview_content": OptionInfo("Prompt", "Live preview subject", gr.Radio, {"choices": ["Combined", "Prompt", "Negative prompt"]}),
"live_preview_refresh_period": OptionInfo(1000, "Progressbar/preview update period, in milliseconds")
}))
options_templates.update(options_section(('sampler-params', "Sampler parameters"), {
@ -646,3 +659,17 @@ mem_mon.start()
def listfiles(dirname):
filenames = [os.path.join(dirname, x) for x in sorted(os.listdir(dirname)) if not x.startswith(".")]
return [file for file in filenames if os.path.isfile(file)]
def html_path(filename):
return os.path.join(script_path, "html", filename)
def html(filename):
path = html_path(filename)
if os.path.exists(path):
with open(path, encoding="utf8") as file:
return file.read()
return ""

12
modules/styles.py
View File

@ -40,12 +40,18 @@ def apply_styles_to_prompt(prompt, styles):
class StyleDatabase:
def __init__(self, path: str):
self.no_style = PromptStyle("None", "", "")
self.styles = {"None": self.no_style}
self.styles = {}
self.path = path
if not os.path.exists(path):
self.reload()
def reload(self):
self.styles.clear()
if not os.path.exists(self.path):
return
with open(path, "r", encoding="utf-8-sig", newline='') as file:
with open(self.path, "r", encoding="utf-8-sig", newline='') as file:
reader = csv.DictReader(file)
for row in reader:
# Support loading old CSV format with "name, text"-columns

2
modules/textual_inversion/logging.py
View File

@ -2,7 +2,7 @@ import datetime
import json
import os
saved_params_shared = {"model_name", "model_hash", "initial_step", "num_of_dataset_images", "learn_rate", "batch_size", "clip_grad_mode", "clip_grad_value", "gradient_step", "data_root", "log_directory", "training_width", "training_height", "steps", "create_image_every", "template_file"}
saved_params_shared = {"model_name", "model_hash", "initial_step", "num_of_dataset_images", "learn_rate", "batch_size", "clip_grad_mode", "clip_grad_value", "gradient_step", "data_root", "log_directory", "training_width", "training_height", "steps", "create_image_every", "template_file", "gradient_step", "latent_sampling_method"}
saved_params_ti = {"embedding_name", "num_vectors_per_token", "save_embedding_every", "save_image_with_stored_embedding"}
saved_params_hypernet = {"hypernetwork_name", "layer_structure", "activation_func", "weight_init", "add_layer_norm", "use_dropout", "save_hypernetwork_every"}
saved_params_all = saved_params_shared | saved_params_ti | saved_params_hypernet

36
modules/textual_inversion/preprocess.py
View File

@ -12,7 +12,7 @@ from modules.shared import opts, cmd_opts
from modules.textual_inversion import autocrop
def preprocess(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False):
def preprocess(id_task, process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
try:
if process_caption:
shared.interrogator.load()
@ -20,7 +20,7 @@ def preprocess(process_src, process_dst, process_width, process_height, preproce
if process_caption_deepbooru:
deepbooru.model.start()
preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug)
preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug, process_multicrop, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold)
finally:
@ -109,8 +109,30 @@ def split_pic(image, inverse_xy, width, height, overlap_ratio):
splitted = image.crop((0, y, to_w, y + to_h))
yield splitted
# not using torchvision.transforms.CenterCrop because it doesn't allow float regions
def center_crop(image: Image, w: int, h: int):
iw, ih = image.size
if ih / h < iw / w:
sw = w * ih / h
box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih
else:
sh = h * iw / w
box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2
return image.resize((w, h), Image.Resampling.LANCZOS, box)
def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False):
def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold):
iw, ih = image.size
err = lambda w, h: 1-(lambda x: x if x < 1 else 1/x)(iw/ih/(w/h))
wh = max(((w, h) for w in range(mindim, maxdim+1, 64) for h in range(mindim, maxdim+1, 64)
if minarea <= w * h <= maxarea and err(w, h) <= threshold),
key= lambda wh: (wh[0]*wh[1], -err(*wh))[::1 if objective=='Maximize area' else -1],
default=None
)
return wh and center_crop(image, *wh)
def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
width = process_width
height = process_height
src = os.path.abspath(process_src)
@ -194,6 +216,14 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre
save_pic(focal, index, params, existing_caption=existing_caption)
process_default_resize = False
if process_multicrop:
cropped = multicrop_pic(img, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold)
if cropped is not None:
save_pic(cropped, index, params, existing_caption=existing_caption)
else:
print(f"skipped {img.width}x{img.height} image {filename} (can't find suitable size within error threshold)")
process_default_resize = False
if process_default_resize:
img = images.resize_image(1, img, width, height)
save_pic(img, index, params, existing_caption=existing_caption)

14
modules/textual_inversion/textual_inversion.py
View File

@ -15,7 +15,7 @@ import numpy as np
from PIL import Image, PngImagePlugin
from torch.utils.tensorboard import SummaryWriter
from modules import shared, devices, sd_hijack, processing, sd_models, images, sd_samplers
from modules import shared, devices, sd_hijack, processing, sd_models, images, sd_samplers, sd_hijack_checkpoint
import modules.textual_inversion.dataset
from modules.textual_inversion.learn_schedule import LearnRateScheduler
@ -50,6 +50,7 @@ class Embedding:
self.sd_checkpoint = None
self.sd_checkpoint_name = None
self.optimizer_state_dict = None
self.filename = None
def save(self, filename):
embedding_data = {
@ -182,6 +183,7 @@ class EmbeddingDatabase:
embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None)
embedding.vectors = vec.shape[0]
embedding.shape = vec.shape[-1]
embedding.filename = path
if self.expected_shape == -1 or self.expected_shape == embedding.shape:
self.register_embedding(embedding, shared.sd_model)
@ -345,7 +347,7 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat
assert log_directory, "Log directory is empty"
def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
save_embedding_every = save_embedding_every or 0
create_image_every = create_image_every or 0
template_file = textual_inversion_templates.get(template_filename, None)
@ -452,6 +454,8 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
pbar = tqdm.tqdm(total=steps - initial_step)
try:
sd_hijack_checkpoint.add()
for i in range((steps-initial_step) * gradient_step):
if scheduler.finished:
break
@ -510,7 +514,6 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
description = f"Training textual inversion [Epoch {epoch_num}: {epoch_step+1}/{steps_per_epoch}] loss: {loss_step:.7f}"
pbar.set_description(description)
shared.state.textinfo = description
if embedding_dir is not None and steps_done % save_embedding_every == 0:
# Before saving, change name to match current checkpoint.
embedding_name_every = f'{embedding_name}-{steps_done}'
@ -560,7 +563,8 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
shared.sd_model.first_stage_model.to(devices.cpu)
if image is not None:
shared.state.current_image = image
shared.state.assign_current_image(image)
last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename, save_to_dirs=False)
last_saved_image += f", prompt: {preview_text}"
@ -617,9 +621,11 @@ Last saved image: {html.escape(last_saved_image)}<br/>
pbar.close()
shared.sd_model.first_stage_model.to(devices.device)
shared.parallel_processing_allowed = old_parallel_processing_allowed
sd_hijack_checkpoint.remove()
return embedding, filename
def save_embedding(embedding, optimizer, checkpoint, embedding_name, filename, remove_cached_checksum=True):
old_embedding_name = embedding.name
old_sd_checkpoint = embedding.sd_checkpoint if hasattr(embedding, "sd_checkpoint") else None

4
modules/txt2img.py
View File

@ -8,13 +8,13 @@ import modules.processing as processing
from modules.ui import plaintext_to_html
def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, *args):
def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, *args):
p = StableDiffusionProcessingTxt2Img(
sd_model=shared.sd_model,
outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples,
outpath_grids=opts.outdir_grids or opts.outdir_txt2img_grids,
prompt=prompt,
styles=[prompt_style, prompt_style2],
styles=prompt_styles,
negative_prompt=negative_prompt,
seed=seed,
subseed=subseed,

483
modules/ui.py
View File

@ -11,6 +11,7 @@ import tempfile
import time
import traceback
from functools import partial, reduce
import warnings
import gradio as gr
import gradio.routes
@ -19,7 +20,7 @@ import numpy as np
from PIL import Image, PngImagePlugin
from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, wrap_gradio_call
from modules import sd_hijack, sd_models, localization, script_callbacks, ui_extensions, deepbooru
from modules import sd_hijack, sd_models, localization, script_callbacks, ui_extensions, deepbooru, sd_vae, extra_networks
from modules.ui_components import FormRow, FormGroup, ToolButton, FormHTML
from modules.paths import script_path
@ -41,6 +42,8 @@ from modules.textual_inversion import textual_inversion
import modules.hypernetworks.ui
from modules.generation_parameters_copypaste import image_from_url_text
warnings.filterwarnings("default" if opts.show_warnings else "ignore", category=UserWarning)
# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the browser will not show any UI
mimetypes.init()
mimetypes.add_type('application/javascript', '.js')
@ -72,6 +75,7 @@ css_hide_progressbar = """
.wrap .m-12::before { content:"Loading..." }
.wrap .z-20 svg { display:none!important; }
.wrap .z-20::before { content:"Loading..." }
.wrap.cover-bg .z-20::before { content:"" }
.progress-bar { display:none!important; }
.meta-text { display:none!important; }
.meta-text-center { display:none!important; }
@ -87,6 +91,7 @@ refresh_symbol = '\U0001f504' # 🔄
save_style_symbol = '\U0001f4be' # 💾
apply_style_symbol = '\U0001f4cb' # 📋
clear_prompt_symbol = '\U0001F5D1' # 🗑️
extra_networks_symbol = '\U0001F3B4' # 🎴
def plaintext_to_html(text):
@ -180,7 +185,7 @@ def add_style(name: str, prompt: str, negative_prompt: str):
# reserialize all styles every time we save them
shared.prompt_styles.save_styles(shared.styles_filename)
return [gr.Dropdown.update(visible=True, choices=list(shared.prompt_styles.styles)) for _ in range(4)]
return [gr.Dropdown.update(visible=True, choices=list(shared.prompt_styles.styles)) for _ in range(2)]
def calc_resolution_hires(enable, width, height, hr_scale, hr_resize_x, hr_resize_y):
@ -197,22 +202,44 @@ def calc_resolution_hires(enable, width, height, hr_scale, hr_resize_x, hr_resiz
return f"resize: from <span class='resolution'>{p.width}x{p.height}</span> to <span class='resolution'>{p.hr_resize_x or p.hr_upscale_to_x}x{p.hr_resize_y or p.hr_upscale_to_y}</span>"
def apply_styles(prompt, prompt_neg, style1_name, style2_name):
prompt = shared.prompt_styles.apply_styles_to_prompt(prompt, [style1_name, style2_name])
prompt_neg = shared.prompt_styles.apply_negative_styles_to_prompt(prompt_neg, [style1_name, style2_name])
def apply_styles(prompt, prompt_neg, styles):
prompt = shared.prompt_styles.apply_styles_to_prompt(prompt, styles)
prompt_neg = shared.prompt_styles.apply_negative_styles_to_prompt(prompt_neg, styles)
return [gr.Textbox.update(value=prompt), gr.Textbox.update(value=prompt_neg), gr.Dropdown.update(value="None"), gr.Dropdown.update(value="None")]
return [gr.Textbox.update(value=prompt), gr.Textbox.update(value=prompt_neg), gr.Dropdown.update(value=[])]
def process_interrogate(interrogation_function, mode, ii_input_dir, ii_output_dir, *ii_singles):
if mode in {0, 1, 3, 4}:
return [interrogation_function(ii_singles[mode]), None]
elif mode == 2:
return [interrogation_function(ii_singles[mode]["image"]), None]
elif mode == 5:
assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
images = shared.listfiles(ii_input_dir)
print(f"Will process {len(images)} images.")
if ii_output_dir != "":
os.makedirs(ii_output_dir, exist_ok=True)
else:
ii_output_dir = ii_input_dir
for image in images:
img = Image.open(image)
filename = os.path.basename(image)
left, _ = os.path.splitext(filename)
print(interrogation_function(img), file=open(os.path.join(ii_output_dir, left + ".txt"), 'a'))
return [gr.update(), None]
def interrogate(image):
prompt = shared.interrogator.interrogate(image.convert("RGB"))
return gr_show(True) if prompt is None else prompt
return gr.update() if prompt is None else prompt
def interrogate_deepbooru(image):
prompt = deepbooru.model.tag(image)
return gr_show(True) if prompt is None else prompt
return gr.update() if prompt is None else prompt
def create_seed_inputs(target_interface):
@ -299,6 +326,8 @@ def connect_reuse_seed(seed: gr.Number, reuse_seed: gr.Button, generation_info:
def update_token_counter(text, steps):
try:
text, _ = extra_networks.parse_prompt(text)
_, prompt_flat_list, _ = prompt_parser.get_multicond_prompt_list([text])
prompt_schedules = prompt_parser.get_learned_conditioning_prompt_schedules(prompt_flat_list, steps)
@ -310,43 +339,23 @@ def update_token_counter(text, steps):
flat_prompts = reduce(lambda list1, list2: list1+list2, prompt_schedules)
prompts = [prompt_text for step, prompt_text in flat_prompts]
token_count, max_length = max([model_hijack.get_prompt_lengths(prompt) for prompt in prompts], key=lambda args: args[0])
style_class = ' class="red"' if (token_count > max_length) else ""
return f"<span {style_class}>{token_count}/{max_length}</span>"
return f"<span class='gr-box gr-text-input'>{token_count}/{max_length}</span>"
def create_toprow(is_img2img):
id_part = "img2img" if is_img2img else "txt2img"
with gr.Row(elem_id="toprow"):
with gr.Column(scale=6):
with gr.Row(elem_id=f"{id_part}_toprow", variant="compact"):
with gr.Column(elem_id=f"{id_part}_prompt_container", scale=6):
with gr.Row():
with gr.Column(scale=80):
with gr.Row():
prompt = gr.Textbox(label="Prompt", elem_id=f"{id_part}_prompt", show_label=False, lines=2,
placeholder="Prompt (press Ctrl+Enter or Alt+Enter to generate)"
)
prompt = gr.Textbox(label="Prompt", elem_id=f"{id_part}_prompt", show_label=False, lines=3, placeholder="Prompt (press Ctrl+Enter or Alt+Enter to generate)")
with gr.Row():
with gr.Column(scale=80):
with gr.Row():
negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{id_part}_neg_prompt", show_label=False, lines=2,
placeholder="Negative prompt (press Ctrl+Enter or Alt+Enter to generate)"
)
with gr.Column(scale=1, elem_id="roll_col"):
paste = gr.Button(value=paste_symbol, elem_id="paste")
save_style = gr.Button(value=save_style_symbol, elem_id="style_create")
prompt_style_apply = gr.Button(value=apply_style_symbol, elem_id="style_apply")
clear_prompt_button = gr.Button(value=clear_prompt_symbol, elem_id=f"{id_part}_clear_prompt")
token_counter = gr.HTML(value="<span></span>", elem_id=f"{id_part}_token_counter")
token_button = gr.Button(visible=False, elem_id=f"{id_part}_token_button")
clear_prompt_button.click(
fn=lambda *x: x,
_js="confirm_clear_prompt",
inputs=[prompt, negative_prompt],
outputs=[prompt, negative_prompt],
)
negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{id_part}_neg_prompt", show_label=False, lines=2, placeholder="Negative prompt (press Ctrl+Enter or Alt+Enter to generate)")
button_interrogate = None
button_deepbooru = None
@ -355,10 +364,10 @@ def create_toprow(is_img2img):
button_interrogate = gr.Button('Interrogate\nCLIP', elem_id="interrogate")
button_deepbooru = gr.Button('Interrogate\nDeepBooru', elem_id="deepbooru")
with gr.Column(scale=1):
with gr.Row():
skip = gr.Button('Skip', elem_id=f"{id_part}_skip")
with gr.Column(scale=1, elem_id=f"{id_part}_actions_column"):
with gr.Row(elem_id=f"{id_part}_generate_box"):
interrupt = gr.Button('Interrupt', elem_id=f"{id_part}_interrupt")
skip = gr.Button('Skip', elem_id=f"{id_part}_skip")
submit = gr.Button('Generate', elem_id=f"{id_part}_generate", variant='primary')
skip.click(
@ -373,20 +382,34 @@ def create_toprow(is_img2img):
outputs=[],
)
with gr.Row():
with gr.Column(scale=1, elem_id="style_pos_col"):
prompt_style = gr.Dropdown(label="Style 1", elem_id=f"{id_part}_style_index", choices=[k for k, v in shared.prompt_styles.styles.items()], value=next(iter(shared.prompt_styles.styles.keys())))
with gr.Row(elem_id=f"{id_part}_tools"):
paste = ToolButton(value=paste_symbol, elem_id="paste")
clear_prompt_button = ToolButton(value=clear_prompt_symbol, elem_id=f"{id_part}_clear_prompt")
extra_networks_button = ToolButton(value=extra_networks_symbol, elem_id=f"{id_part}_extra_networks")
prompt_style_apply = ToolButton(value=apply_style_symbol, elem_id=f"{id_part}_style_apply")
save_style = ToolButton(value=save_style_symbol, elem_id=f"{id_part}_style_create")
with gr.Column(scale=1, elem_id="style_neg_col"):
prompt_style2 = gr.Dropdown(label="Style 2", elem_id=f"{id_part}_style2_index", choices=[k for k, v in shared.prompt_styles.styles.items()], value=next(iter(shared.prompt_styles.styles.keys())))
token_counter = gr.HTML(value="<span></span>", elem_id=f"{id_part}_token_counter")
token_button = gr.Button(visible=False, elem_id=f"{id_part}_token_button")
negative_token_counter = gr.HTML(value="<span></span>", elem_id=f"{id_part}_negative_token_counter")
negative_token_button = gr.Button(visible=False, elem_id=f"{id_part}_negative_token_button")
return prompt, prompt_style, negative_prompt, prompt_style2, submit, button_interrogate, button_deepbooru, prompt_style_apply, save_style, paste, token_counter, token_button
clear_prompt_button.click(
fn=lambda *x: x,
_js="confirm_clear_prompt",
inputs=[prompt, negative_prompt],
outputs=[prompt, negative_prompt],
)
with gr.Row(elem_id=f"{id_part}_styles_row"):
prompt_styles = gr.Dropdown(label="Styles", elem_id=f"{id_part}_styles", choices=[k for k, v in shared.prompt_styles.styles.items()], value=[], multiselect=True)
create_refresh_button(prompt_styles, shared.prompt_styles.reload, lambda: {"choices": [k for k, v in shared.prompt_styles.styles.items()]}, f"refresh_{id_part}_styles")
return prompt, prompt_styles, negative_prompt, submit, button_interrogate, button_deepbooru, prompt_style_apply, save_style, paste, extra_networks_button, token_counter, token_button, negative_token_counter, negative_token_button
def setup_progressbar(*args, **kwargs):
import modules.ui_progress
modules.ui_progress.setup_progressbar(*args, **kwargs)
pass
def apply_setting(key, value):
@ -419,20 +442,19 @@ def apply_setting(key, value):
opts.data_labels[key].onchange()
opts.save(shared.config_filename)
return value
return getattr(opts, key)
def update_generation_info(args):
generation_info, html_info, img_index = args
def update_generation_info(generation_info, html_info, img_index):
try:
generation_info = json.loads(generation_info)
if img_index < 0 or img_index >= len(generation_info["infotexts"]):
return html_info
return plaintext_to_html(generation_info["infotexts"][img_index])
return html_info, gr.update()
return plaintext_to_html(generation_info["infotexts"][img_index]), gr.update()
except Exception:
pass
# if the json parse or anything else fails, just return the old html_info
return html_info
return html_info, gr.update()
def create_refresh_button(refresh_component, refresh_method, refreshed_args, elem_id):
@ -479,8 +501,8 @@ Requested path was: {f}
else:
sp.Popen(["xdg-open", path])
with gr.Column(variant='panel'):
with gr.Group():
with gr.Column(variant='panel', elem_id=f"{tabname}_results"):
with gr.Group(elem_id=f"{tabname}_gallery_container"):
result_gallery = gr.Gallery(label='Output', show_label=False, elem_id=f"{tabname}_gallery").style(grid=4)
generation_info = None
@ -513,10 +535,9 @@ Requested path was: {f}
generation_info_button = gr.Button(visible=False, elem_id=f"{tabname}_generation_info_button")
generation_info_button.click(
fn=update_generation_info,
_js="(x, y) => [x, y, selected_gallery_index()]",
inputs=[generation_info, html_info],
outputs=[html_info],
preprocess=False
_js="function(x, y, z){ return [x, y, selected_gallery_index()] }",
inputs=[generation_info, html_info, html_info],
outputs=[html_info, html_info],
)
save.click(
@ -531,7 +552,8 @@ Requested path was: {f}
outputs=[
download_files,
html_log,
]
],
show_progress=False,
)
save_zip.click(
@ -572,12 +594,22 @@ def create_sampler_and_steps_selection(choices, tabname):
def ordered_ui_categories():
user_order = {x.strip(): i for i, x in enumerate(shared.opts.ui_reorder.split(","))}
user_order = {x.strip(): i * 2 + 1 for i, x in enumerate(shared.opts.ui_reorder.split(","))}
for i, category in sorted(enumerate(shared.ui_reorder_categories), key=lambda x: user_order.get(x[1], x[0] + 1000)):
for i, category in sorted(enumerate(shared.ui_reorder_categories), key=lambda x: user_order.get(x[1], x[0] * 2 + 0)):
yield category
def get_value_for_setting(key):
value = getattr(opts, key)
info = opts.data_labels[key]
args = info.component_args() if callable(info.component_args) else info.component_args or {}
args = {k: v for k, v in args.items() if k not in {'precision'}}
return gr.update(value=value, **args)
def create_ui():
import modules.img2img
import modules.txt2img
@ -590,22 +622,17 @@ def create_ui():
modules.scripts.scripts_txt2img.initialize_scripts(is_img2img=False)
with gr.Blocks(analytics_enabled=False) as txt2img_interface:
txt2img_prompt, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, _,txt2img_prompt_style_apply, txt2img_save_style, txt2img_paste, token_counter, token_button = create_toprow(is_img2img=False)
txt2img_prompt, txt2img_prompt_styles, txt2img_negative_prompt, submit, _, _, txt2img_prompt_style_apply, txt2img_save_style, txt2img_paste, extra_networks_button, token_counter, token_button, negative_token_counter, negative_token_button = create_toprow(is_img2img=False)
dummy_component = gr.Label(visible=False)
txt_prompt_img = gr.File(label="", elem_id="txt2img_prompt_image", file_count="single", type="bytes", visible=False)
txt_prompt_img = gr.File(label="", elem_id="txt2img_prompt_image", file_count="single", type="binary", visible=False)
with gr.Row(elem_id='txt2img_progress_row'):
with gr.Column(scale=1):
pass
with gr.Column(scale=1):
progressbar = gr.HTML(elem_id="txt2img_progressbar")
txt2img_preview = gr.Image(elem_id='txt2img_preview', visible=False)
setup_progressbar(progressbar, txt2img_preview, 'txt2img')
with FormRow(variant='compact', elem_id="txt2img_extra_networks", visible=False) as extra_networks:
from modules import ui_extra_networks
extra_networks_ui = ui_extra_networks.create_ui(extra_networks, extra_networks_button, 'txt2img')
with gr.Row().style(equal_height=False):
with gr.Column(variant='panel', elem_id="txt2img_settings"):
with gr.Column(variant='compact', elem_id="txt2img_settings"):
for category in ordered_ui_categories():
if category == "sampler":
steps, sampler_index = create_sampler_and_steps_selection(samplers, "txt2img")
@ -628,7 +655,7 @@ def create_ui():
seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('txt2img')
elif category == "checkboxes":
with FormRow(elem_id="txt2img_checkboxes"):
with FormRow(elem_id="txt2img_checkboxes", variant="compact"):
restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="txt2img_restore_faces")
tiling = gr.Checkbox(label='Tiling', value=False, elem_id="txt2img_tiling")
enable_hr = gr.Checkbox(label='Hires. fix', value=False, elem_id="txt2img_enable_hr")
@ -636,12 +663,12 @@ def create_ui():
elif category == "hires_fix":
with FormGroup(visible=False, elem_id="txt2img_hires_fix") as hr_options:
with FormRow(elem_id="txt2img_hires_fix_row1"):
with FormRow(elem_id="txt2img_hires_fix_row1", variant="compact"):
hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
hr_second_pass_steps = gr.Slider(minimum=0, maximum=150, step=1, label='Hires steps', value=0, elem_id="txt2img_hires_steps")
denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
with FormRow(elem_id="txt2img_hires_fix_row2"):
with FormRow(elem_id="txt2img_hires_fix_row2", variant="compact"):
hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
hr_resize_x = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize width to", value=0, elem_id="txt2img_hr_resize_x")
hr_resize_y = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize height to", value=0, elem_id="txt2img_hr_resize_y")
@ -682,10 +709,10 @@ def create_ui():
fn=wrap_gradio_gpu_call(modules.txt2img.txt2img, extra_outputs=[None, '', '']),
_js="submit",
inputs=[
dummy_component,
txt2img_prompt,
txt2img_negative_prompt,
txt2img_prompt_style,
txt2img_prompt_style2,
txt2img_prompt_styles,
steps,
sampler_index,
restore_faces,
@ -775,39 +802,57 @@ def create_ui():
]
token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[txt2img_prompt, steps], outputs=[token_counter])
negative_token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[txt2img_negative_prompt, steps], outputs=[negative_token_counter])
ui_extra_networks.setup_ui(extra_networks_ui, txt2img_gallery)
modules.scripts.scripts_current = modules.scripts.scripts_img2img
modules.scripts.scripts_img2img.initialize_scripts(is_img2img=True)
with gr.Blocks(analytics_enabled=False) as img2img_interface:
img2img_prompt, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_deepbooru, img2img_prompt_style_apply, img2img_save_style, img2img_paste,token_counter, token_button = create_toprow(is_img2img=True)
img2img_prompt, img2img_prompt_styles, img2img_negative_prompt, submit, img2img_interrogate, img2img_deepbooru, img2img_prompt_style_apply, img2img_save_style, img2img_paste, extra_networks_button, token_counter, token_button, negative_token_counter, negative_token_button = create_toprow(is_img2img=True)
with gr.Row(elem_id='img2img_progress_row'):
img2img_prompt_img = gr.File(label="", elem_id="img2img_prompt_image", file_count="single", type="bytes", visible=False)
img2img_prompt_img = gr.File(label="", elem_id="img2img_prompt_image", file_count="single", type="binary", visible=False)
with gr.Column(scale=1):
pass
with gr.Column(scale=1):
progressbar = gr.HTML(elem_id="img2img_progressbar")
img2img_preview = gr.Image(elem_id='img2img_preview', visible=False)
setup_progressbar(progressbar, img2img_preview, 'img2img')
with FormRow(variant='compact', elem_id="img2img_extra_networks", visible=False) as extra_networks:
from modules import ui_extra_networks
extra_networks_ui_img2img = ui_extra_networks.create_ui(extra_networks, extra_networks_button, 'img2img')
with FormRow().style(equal_height=False):
with gr.Column(variant='panel', elem_id="img2img_settings"):
with gr.Column(variant='compact', elem_id="img2img_settings"):
copy_image_buttons = []
copy_image_destinations = {}
def add_copy_image_controls(tab_name, elem):
with gr.Row(variant="compact", elem_id=f"img2img_copy_to_{tab_name}"):
gr.HTML("Copy image to: ", elem_id=f"img2img_label_copy_to_{tab_name}")
for title, name in zip(['img2img', 'sketch', 'inpaint', 'inpaint sketch'], ['img2img', 'sketch', 'inpaint', 'inpaint_sketch']):
if name == tab_name:
gr.Button(title, interactive=False)
copy_image_destinations[name] = elem
continue
button = gr.Button(title)
copy_image_buttons.append((button, name, elem))
with gr.Tabs(elem_id="mode_img2img"):
with gr.TabItem('img2img', id='img2img', elem_id="img2img_img2img_tab") as tab_img2img:
init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool="editor", image_mode="RGBA").style(height=480)
add_copy_image_controls('img2img', init_img)
with gr.TabItem('Sketch', id='img2img_sketch', elem_id="img2img_img2img_sketch_tab") as tab_sketch:
sketch = gr.Image(label="Image for img2img", elem_id="img2img_sketch", show_label=False, source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGBA").style(height=480)
add_copy_image_controls('sketch', sketch)
with gr.TabItem('Inpaint', id='inpaint', elem_id="img2img_inpaint_tab") as tab_inpaint:
init_img_with_mask = gr.Image(label="Image for inpainting with mask", show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool="sketch", image_mode="RGBA").style(height=480)
add_copy_image_controls('inpaint', init_img_with_mask)
with gr.TabItem('Inpaint sketch', id='inpaint_sketch', elem_id="img2img_inpaint_sketch_tab") as tab_inpaint_color:
inpaint_color_sketch = gr.Image(label="Color sketch inpainting", show_label=False, elem_id="inpaint_sketch", source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGBA").style(height=480)
inpaint_color_sketch_orig = gr.State(None)
add_copy_image_controls('inpaint_sketch', inpaint_color_sketch)
def update_orig(image, state):
if image is not None:
@ -824,36 +869,27 @@ def create_ui():
with gr.TabItem('Batch', id='batch', elem_id="img2img_batch_tab") as tab_batch:
hidden = '<br>Disabled when launched with --hide-ui-dir-config.' if shared.cmd_opts.hide_ui_dir_config else ''
gr.HTML(f"<p class=\"text-gray-500\">Process images in a directory on the same machine where the server is running.<br>Use an empty output directory to save pictures normally instead of writing to the output directory.{hidden}</p>")
gr.HTML(f"<p style='padding-bottom: 1em;' class=\"text-gray-500\">Process images in a directory on the same machine where the server is running.<br>Use an empty output directory to save pictures normally instead of writing to the output directory.{hidden}</p>")
img2img_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs, elem_id="img2img_batch_input_dir")
img2img_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, elem_id="img2img_batch_output_dir")
with FormGroup(elem_id="inpaint_controls", visible=False) as inpaint_controls:
with FormRow():
mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4, elem_id="img2img_mask_blur")
mask_alpha = gr.Slider(label="Mask transparency", visible=False, elem_id="img2img_mask_alpha")
def copy_image(img):
if isinstance(img, dict) and 'image' in img:
return img['image']
with FormRow():
inpainting_mask_invert = gr.Radio(label='Mask mode', choices=['Inpaint masked', 'Inpaint not masked'], value='Inpaint masked', type="index", elem_id="img2img_mask_mode")
return img
with FormRow():
inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='original', type="index", elem_id="img2img_inpainting_fill")
with FormRow():
with gr.Column():
inpaint_full_res = gr.Radio(label="Inpaint area", choices=["Whole picture", "Only masked"], type="index", value="Whole picture", elem_id="img2img_inpaint_full_res")
with gr.Column(scale=4):
inpaint_full_res_padding = gr.Slider(label='Only masked padding, pixels', minimum=0, maximum=256, step=4, value=32, elem_id="img2img_inpaint_full_res_padding")
def select_img2img_tab(tab):
return gr.update(visible=tab in [2, 3, 4]), gr.update(visible=tab == 3),
for i, elem in enumerate([tab_img2img, tab_sketch, tab_inpaint, tab_inpaint_color, tab_inpaint_upload, tab_batch]):
elem.select(
fn=lambda tab=i: select_img2img_tab(tab),
for button, name, elem in copy_image_buttons:
button.click(
fn=copy_image,
inputs=[elem],
outputs=[copy_image_destinations[name]],
)
button.click(
fn=lambda: None,
_js="switch_to_"+name.replace(" ", "_"),
inputs=[],
outputs=[inpaint_controls, mask_alpha],
outputs=[],
)
with FormRow():
@ -897,6 +933,35 @@ def create_ui():
with FormGroup(elem_id="img2img_script_container"):
custom_inputs = modules.scripts.scripts_img2img.setup_ui()
elif category == "inpaint":
with FormGroup(elem_id="inpaint_controls", visible=False) as inpaint_controls:
with FormRow():
mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4, elem_id="img2img_mask_blur")
mask_alpha = gr.Slider(label="Mask transparency", visible=False, elem_id="img2img_mask_alpha")
with FormRow():
inpainting_mask_invert = gr.Radio(label='Mask mode', choices=['Inpaint masked', 'Inpaint not masked'], value='Inpaint masked', type="index", elem_id="img2img_mask_mode")
with FormRow():
inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='original', type="index", elem_id="img2img_inpainting_fill")
with FormRow():
with gr.Column():
inpaint_full_res = gr.Radio(label="Inpaint area", choices=["Whole picture", "Only masked"], type="index", value="Whole picture", elem_id="img2img_inpaint_full_res")
with gr.Column(scale=4):
inpaint_full_res_padding = gr.Slider(label='Only masked padding, pixels', minimum=0, maximum=256, step=4, value=32, elem_id="img2img_inpaint_full_res_padding")
def select_img2img_tab(tab):
return gr.update(visible=tab in [2, 3, 4]), gr.update(visible=tab == 3),
for i, elem in enumerate([tab_img2img, tab_sketch, tab_inpaint, tab_inpaint_color, tab_inpaint_upload, tab_batch]):
elem.select(
fn=lambda tab=i: select_img2img_tab(tab),
inputs=[],
outputs=[inpaint_controls, mask_alpha],
)
img2img_gallery, generation_info, html_info, html_log = create_output_panel("img2img", opts.outdir_img2img_samples)
parameters_copypaste.bind_buttons({"img2img": img2img_paste}, None, img2img_prompt)
@ -918,11 +983,11 @@ def create_ui():
fn=wrap_gradio_gpu_call(modules.img2img.img2img, extra_outputs=[None, '', '']),
_js="submit_img2img",
inputs=[
dummy_component,
dummy_component,
img2img_prompt,
img2img_negative_prompt,
img2img_prompt_style,
img2img_prompt_style2,
img2img_prompt_styles,
init_img,
sketch,
init_img_with_mask,
@ -961,23 +1026,36 @@ def create_ui():
show_progress=False,
)
interrogate_args = dict(
_js="get_img2img_tab_index",
inputs=[
dummy_component,
img2img_batch_input_dir,
img2img_batch_output_dir,
init_img,
sketch,
init_img_with_mask,
inpaint_color_sketch,
init_img_inpaint,
],
outputs=[img2img_prompt, dummy_component],
)
img2img_prompt.submit(**img2img_args)
submit.click(**img2img_args)
img2img_interrogate.click(
fn=interrogate,
inputs=[init_img],
outputs=[img2img_prompt],
fn=lambda *args: process_interrogate(interrogate, *args),
**interrogate_args,
)
img2img_deepbooru.click(
fn=interrogate_deepbooru,
inputs=[init_img],
outputs=[img2img_prompt],
fn=lambda *args: process_interrogate(interrogate_deepbooru, *args),
**interrogate_args,
)
prompts = [(txt2img_prompt, txt2img_negative_prompt), (img2img_prompt, img2img_negative_prompt)]
style_dropdowns = [(txt2img_prompt_style, txt2img_prompt_style2), (img2img_prompt_style, img2img_prompt_style2)]
style_dropdowns = [txt2img_prompt_styles, img2img_prompt_styles]
style_js_funcs = ["update_txt2img_tokens", "update_img2img_tokens"]
for button, (prompt, negative_prompt) in zip([txt2img_save_style, img2img_save_style], prompts):
@ -987,18 +1065,21 @@ def create_ui():
# Have to pass empty dummy component here, because the JavaScript and Python function have to accept
# the same number of parameters, but we only know the style-name after the JavaScript prompt
inputs=[dummy_component, prompt, negative_prompt],
outputs=[txt2img_prompt_style, img2img_prompt_style, txt2img_prompt_style2, img2img_prompt_style2],
outputs=[txt2img_prompt_styles, img2img_prompt_styles],
)
for button, (prompt, negative_prompt), (style1, style2), js_func in zip([txt2img_prompt_style_apply, img2img_prompt_style_apply], prompts, style_dropdowns, style_js_funcs):
for button, (prompt, negative_prompt), styles, js_func in zip([txt2img_prompt_style_apply, img2img_prompt_style_apply], prompts, style_dropdowns, style_js_funcs):
button.click(
fn=apply_styles,
_js=js_func,
inputs=[prompt, negative_prompt, style1, style2],
outputs=[prompt, negative_prompt, style1, style2],
inputs=[prompt, negative_prompt, styles],
outputs=[prompt, negative_prompt, styles],
)
token_button.click(fn=update_token_counter, inputs=[img2img_prompt, steps], outputs=[token_counter])
negative_token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[txt2img_negative_prompt, steps], outputs=[negative_token_counter])
ui_extra_networks.setup_ui(extra_networks_ui_img2img, img2img_gallery)
img2img_paste_fields = [
(img2img_prompt, "Prompt"),
@ -1026,7 +1107,7 @@ def create_ui():
with gr.Blocks(analytics_enabled=False) as extras_interface:
with gr.Row().style(equal_height=False):
with gr.Column(variant='panel'):
with gr.Column(variant='compact'):
with gr.Tabs(elem_id="mode_extras"):
with gr.TabItem('Single Image', elem_id="extras_single_tab"):
extras_image = gr.Image(label="Source", source="upload", interactive=True, type="pil", elem_id="extras_image")
@ -1125,12 +1206,21 @@ def create_ui():
outputs=[html, generation_info, html2],
)
def update_interp_description(value):
interp_description_css = "<p style='margin-bottom: 2.5em'>{}</p>"
interp_descriptions = {
"No interpolation": interp_description_css.format("No interpolation will be used. Requires one model; A. Allows for format conversion and VAE baking."),
"Weighted sum": interp_description_css.format("A weighted sum will be used for interpolation. Requires two models; A and B. The result is calculated as A * (1 - M) + B * M"),
"Add difference": interp_description_css.format("The difference between the last two models will be added to the first. Requires three models; A, B and C. The result is calculated as A + (B - C) * M")
}
return interp_descriptions[value]
with gr.Blocks(analytics_enabled=False) as modelmerger_interface:
with gr.Row().style(equal_height=False):
with gr.Column(variant='panel'):
gr.HTML(value="<p>A merger of the two checkpoints will be generated in your <b>checkpoint</b> directory.</p>")
with gr.Column(variant='compact'):
interp_description = gr.HTML(value=update_interp_description("Weighted sum"), elem_id="modelmerger_interp_description")
with FormRow():
with FormRow(elem_id="modelmerger_models"):
primary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_primary_model_name", label="Primary model (A)")
create_refresh_button(primary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_A")
@ -1142,24 +1232,37 @@ def create_ui():
custom_name = gr.Textbox(label="Custom Name (Optional)", elem_id="modelmerger_custom_name")
interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Multiplier (M) - set to 0 to get model A', value=0.3, elem_id="modelmerger_interp_amount")
interp_method = gr.Radio(choices=["Weighted sum", "Add difference"], value="Weighted sum", label="Interpolation Method", elem_id="modelmerger_interp_method")
interp_method = gr.Radio(choices=["No interpolation", "Weighted sum", "Add difference"], value="Weighted sum", label="Interpolation Method", elem_id="modelmerger_interp_method")
interp_method.change(fn=update_interp_description, inputs=[interp_method], outputs=[interp_description])
with FormRow():
checkpoint_format = gr.Radio(choices=["ckpt", "safetensors"], value="ckpt", label="Checkpoint format", elem_id="modelmerger_checkpoint_format")
save_as_half = gr.Checkbox(value=False, label="Save as float16", elem_id="modelmerger_save_as_half")
config_source = gr.Radio(choices=["A, B or C", "B", "C", "Don't"], value="A, B or C", label="Copy config from", type="index", elem_id="modelmerger_config_method")
with FormRow():
with gr.Column():
config_source = gr.Radio(choices=["A, B or C", "B", "C", "Don't"], value="A, B or C", label="Copy config from", type="index", elem_id="modelmerger_config_method")
modelmerger_merge = gr.Button(elem_id="modelmerger_merge", value="Merge", variant='primary')
with gr.Column():
with FormRow():
bake_in_vae = gr.Dropdown(choices=["None"] + list(sd_vae.vae_dict), value="None", label="Bake in VAE", elem_id="modelmerger_bake_in_vae")
create_refresh_button(bake_in_vae, sd_vae.refresh_vae_list, lambda: {"choices": ["None"] + list(sd_vae.vae_dict)}, "modelmerger_refresh_bake_in_vae")
with gr.Column(variant='panel'):
submit_result = gr.Textbox(elem_id="modelmerger_result", show_label=False)
with FormRow():
discard_weights = gr.Textbox(value="", label="Discard weights with matching name", elem_id="modelmerger_discard_weights")
with gr.Row():
modelmerger_merge = gr.Button(elem_id="modelmerger_merge", value="Merge", variant='primary')
with gr.Column(variant='compact', elem_id="modelmerger_results_container"):
with gr.Group(elem_id="modelmerger_results_panel"):
modelmerger_result = gr.HTML(elem_id="modelmerger_result", show_label=False)
with gr.Blocks(analytics_enabled=False) as train_interface:
with gr.Row().style(equal_height=False):
gr.HTML(value="<p style='margin-bottom: 0.7em'>See <b><a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\">wiki</a></b> for detailed explanation.</p>")
with gr.Row().style(equal_height=False):
with gr.Row(variant="compact").style(equal_height=False):
with gr.Tabs(elem_id="train_tabs"):
with gr.Tab(label="Create embedding"):
@ -1204,6 +1307,7 @@ def create_ui():
process_flip = gr.Checkbox(label='Create flipped copies', elem_id="train_process_flip")
process_split = gr.Checkbox(label='Split oversized images', elem_id="train_process_split")
process_focal_crop = gr.Checkbox(label='Auto focal point crop', elem_id="train_process_focal_crop")
process_multicrop = gr.Checkbox(label='Auto-sized crop', elem_id="train_process_multicrop")
process_caption = gr.Checkbox(label='Use BLIP for caption', elem_id="train_process_caption")
process_caption_deepbooru = gr.Checkbox(label='Use deepbooru for caption', visible=True, elem_id="train_process_caption_deepbooru")
@ -1216,7 +1320,19 @@ def create_ui():
process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_entropy_weight")
process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_edges_weight")
process_focal_crop_debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug")
with gr.Column(visible=False) as process_multicrop_col:
gr.Markdown('Each image is center-cropped with an automatically chosen width and height.')
with gr.Row():
process_multicrop_mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="train_process_multicrop_mindim")
process_multicrop_maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="train_process_multicrop_maxdim")
with gr.Row():
process_multicrop_minarea = gr.Slider(minimum=64*64, maximum=2048*2048, step=1, label="Area lower bound", value=64*64, elem_id="train_process_multicrop_minarea")
process_multicrop_maxarea = gr.Slider(minimum=64*64, maximum=2048*2048, step=1, label="Area upper bound", value=640*640, elem_id="train_process_multicrop_maxarea")
with gr.Row():
process_multicrop_objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="train_process_multicrop_objective")
process_multicrop_threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="train_process_multicrop_threshold")
with gr.Row():
with gr.Column(scale=3):
gr.HTML(value="")
@ -1238,6 +1354,12 @@ def create_ui():
outputs=[process_focal_crop_row],
)
process_multicrop.change(
fn=lambda show: gr_show(show),
inputs=[process_multicrop],
outputs=[process_multicrop_col],
)
def get_textual_inversion_template_names():
return sorted([x for x in textual_inversion.textual_inversion_templates])
@ -1295,15 +1417,11 @@ def create_ui():
script_callbacks.ui_train_tabs_callback(params)
with gr.Column():
progressbar = gr.HTML(elem_id="ti_progressbar")
with gr.Column(elem_id='ti_gallery_container'):
ti_output = gr.Text(elem_id="ti_output", value="", show_label=False)
ti_gallery = gr.Gallery(label='Output', show_label=False, elem_id='ti_gallery').style(grid=4)
ti_preview = gr.Image(elem_id='ti_preview', visible=False)
ti_progress = gr.HTML(elem_id="ti_progress", value="")
ti_outcome = gr.HTML(elem_id="ti_error", value="")
setup_progressbar(progressbar, ti_preview, 'ti', textinfo=ti_progress)
create_embedding.click(
fn=modules.textual_inversion.ui.create_embedding,
@ -1344,6 +1462,7 @@ def create_ui():
fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
_js="start_training_textual_inversion",
inputs=[
dummy_component,
process_src,
process_dst,
process_width,
@ -1360,6 +1479,13 @@ def create_ui():
process_focal_crop_entropy_weight,
process_focal_crop_edges_weight,
process_focal_crop_debug,
process_multicrop,
process_multicrop_mindim,
process_multicrop_maxdim,
process_multicrop_minarea,
process_multicrop_maxarea,
process_multicrop_objective,
process_multicrop_threshold,
],
outputs=[
ti_output,
@ -1371,6 +1497,7 @@ def create_ui():
fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.train_embedding, extra_outputs=[gr.update()]),
_js="start_training_textual_inversion",
inputs=[
dummy_component,
train_embedding_name,
embedding_learn_rate,
batch_size,
@ -1403,6 +1530,7 @@ def create_ui():
fn=wrap_gradio_gpu_call(modules.hypernetworks.ui.train_hypernetwork, extra_outputs=[gr.update()]),
_js="start_training_textual_inversion",
inputs=[
dummy_component,
train_hypernetwork_name,
hypernetwork_learn_rate,
batch_size,
@ -1511,7 +1639,7 @@ def create_ui():
opts.save(shared.config_filename)
return gr.update(value=value), opts.dumpjson()
return get_value_for_setting(key), opts.dumpjson()
with gr.Blocks(analytics_enabled=False) as settings_interface:
with gr.Row():
@ -1529,6 +1657,7 @@ def create_ui():
previous_section = None
current_tab = None
current_row = None
with gr.Tabs(elem_id="settings"):
for i, (k, item) in enumerate(opts.data_labels.items()):
section_must_be_skipped = item.section[0] is None
@ -1537,10 +1666,14 @@ def create_ui():
elem_id, text = item.section
if current_tab is not None:
current_row.__exit__()
current_tab.__exit__()
gr.Group()
current_tab = gr.TabItem(elem_id="settings_{}".format(elem_id), label=text)
current_tab.__enter__()
current_row = gr.Column(variant='compact')
current_row.__enter__()
previous_section = item.section
@ -1555,6 +1688,7 @@ def create_ui():
components.append(component)
if current_tab is not None:
current_row.__exit__()
current_tab.__exit__()
with gr.TabItem("Actions"):
@ -1562,10 +1696,8 @@ def create_ui():
download_localization = gr.Button(value='Download localization template', elem_id="download_localization")
reload_script_bodies = gr.Button(value='Reload custom script bodies (No ui updates, No restart)', variant='secondary', elem_id="settings_reload_script_bodies")
if os.path.exists("html/licenses.html"):
with open("html/licenses.html", encoding="utf8") as file:
with gr.TabItem("Licenses"):
gr.HTML(file.read(), elem_id="licenses")
with gr.TabItem("Licenses"):
gr.HTML(shared.html("licenses.html"), elem_id="licenses")
gr.Button(value="Show all pages", elem_id="settings_show_all_pages")
@ -1636,7 +1768,7 @@ def create_ui():
interfaces += [(extensions_interface, "Extensions", "extensions")]
with gr.Blocks(css=css, analytics_enabled=False, title="Stable Diffusion") as demo:
with gr.Row(elem_id="quicksettings"):
with gr.Row(elem_id="quicksettings", variant="compact"):
for i, k, item in sorted(quicksettings_list, key=lambda x: quicksettings_names.get(x[1], x[0])):
component = create_setting_component(k, is_quicksettings=True)
component_dict[k] = component
@ -1652,11 +1784,9 @@ def create_ui():
if os.path.exists(os.path.join(script_path, "notification.mp3")):
audio_notification = gr.Audio(interactive=False, value=os.path.join(script_path, "notification.mp3"), elem_id="audio_notification", visible=False)
if os.path.exists("html/footer.html"):
with open("html/footer.html", encoding="utf8") as file:
footer = file.read()
footer = footer.format(versions=versions_html())
gr.HTML(footer, elem_id="footer")
footer = shared.html("footer.html")
footer = footer.format(versions=versions_html())
gr.HTML(footer, elem_id="footer")
text_settings = gr.Textbox(elem_id="settings_json", value=lambda: opts.dumpjson(), visible=False)
settings_submit.click(
@ -1677,7 +1807,7 @@ def create_ui():
component_keys = [k for k in opts.data_labels.keys() if k in component_dict]
def get_settings_values():
return [getattr(opts, key) for key in component_keys]
return [get_value_for_setting(key) for key in component_keys]
demo.load(
fn=get_settings_values,
@ -1692,12 +1822,15 @@ def create_ui():
print("Error loading/saving model file:", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
modules.sd_models.list_models() # to remove the potentially missing models from the list
return [f"Error merging checkpoints: {e}"] + [gr.Dropdown.update(choices=modules.sd_models.checkpoint_tiles()) for _ in range(4)]
return [*[gr.Dropdown.update(choices=modules.sd_models.checkpoint_tiles()) for _ in range(4)], f"Error merging checkpoints: {e}"]
return results
modelmerger_merge.click(fn=lambda: '', inputs=[], outputs=[modelmerger_result])
modelmerger_merge.click(
fn=modelmerger,
fn=wrap_gradio_gpu_call(modelmerger, extra_outputs=lambda: [gr.update() for _ in range(4)]),
_js='modelmerger',
inputs=[
dummy_component,
primary_model_name,
secondary_model_name,
tertiary_model_name,
@ -1707,13 +1840,15 @@ def create_ui():
custom_name,
checkpoint_format,
config_source,
bake_in_vae,
discard_weights,
],
outputs=[
submit_result,
primary_model_name,
secondary_model_name,
tertiary_model_name,
component_dict['sd_model_checkpoint'],
modelmerger_result,
]
)
@ -1745,7 +1880,10 @@ def create_ui():
if saved_value is None:
ui_settings[key] = getattr(obj, field)
elif condition and not condition(saved_value):
print(f'Warning: Bad ui setting value: {key}: {saved_value}; Default value "{getattr(obj, field)}" will be used instead.')
pass
# this warning is generally not useful;
# print(f'Warning: Bad ui setting value: {key}: {saved_value}; Default value "{getattr(obj, field)}" will be used instead.')
else:
setattr(obj, field, saved_value)
if init_field is not None:
@ -1773,7 +1911,13 @@ def create_ui():
apply_field(x, 'value')
if type(x) == gr.Dropdown:
apply_field(x, 'value', lambda val: val in x.choices, getattr(x, 'init_field', None))
def check_dropdown(val):
if getattr(x, 'multiselect', False):
return all([value in x.choices for value in val])
else:
return val in x.choices
apply_field(x, 'value', check_dropdown, getattr(x, 'init_field', None))
visit(txt2img_interface, loadsave, "txt2img")
visit(img2img_interface, loadsave, "img2img")
@ -1785,28 +1929,27 @@ def create_ui():
with open(ui_config_file, "w", encoding="utf8") as file:
json.dump(ui_settings, file, indent=4)
# Required as a workaround for change() event not triggering when loading values from ui-config.json
interp_description.value = update_interp_description(interp_method.value)
return demo
def reload_javascript():
with open(os.path.join(script_path, "script.js"), "r", encoding="utf8") as jsfile:
javascript = f'<script>{jsfile.read()}</script>'
scripts_list = modules.scripts.list_scripts("javascript", ".js")
for basedir, filename, path in scripts_list:
with open(path, "r", encoding="utf8") as jsfile:
javascript += f"\n<!-- {filename} --><script>{jsfile.read()}</script>"
head = f'<script type="text/javascript" src="file={os.path.abspath("script.js")}"></script>\n'
inline = f"{localization.localization_js(shared.opts.localization)};"
if cmd_opts.theme is not None:
javascript += f"\n<script>set_theme('{cmd_opts.theme}');</script>\n"
inline += f"set_theme('{cmd_opts.theme}');"
javascript += f"\n<script>{localization.localization_js(shared.opts.localization)}</script>"
head += f'<script type="text/javascript">{inline}</script>\n'
for script in modules.scripts.list_scripts("javascript", ".js"):
head += f'<script type="text/javascript" src="file={script.path}"></script>\n'
def template_response(*args, **kwargs):
res = shared.GradioTemplateResponseOriginal(*args, **kwargs)
res.body = res.body.replace(
b'</head>', f'{javascript}</head>'.encode("utf8"))
res.body = res.body.replace(b'</head>', f'{head}</head>'.encode("utf8"))
res.init_headers()
return res

10
modules/ui_components.py
View File

@ -11,6 +11,16 @@ class ToolButton(gr.Button, gr.components.FormComponent):
return "button"
class ToolButtonTop(gr.Button, gr.components.FormComponent):
"""Small button with single emoji as text, with extra margin at top, fits inside gradio forms"""
def __init__(self, **kwargs):
super().__init__(variant="tool-top", **kwargs)
def get_block_name(self):
return "button"
class FormRow(gr.Row, gr.components.FormComponent):
"""Same as gr.Row but fits inside gradio forms"""

171
modules/ui_extra_networks.py Normal file
View File

@ -0,0 +1,171 @@
import os.path
from modules import shared
import gradio as gr
import json
from modules.generation_parameters_copypaste import image_from_url_text
extra_pages = []
def register_page(page):
"""registers extra networks page for the UI; recommend doing it in on_before_ui() callback for extensions"""
extra_pages.append(page)
class ExtraNetworksPage:
def __init__(self, title):
self.title = title
self.name = title.lower()
self.card_page = shared.html("extra-networks-card.html")
self.allow_negative_prompt = False
def refresh(self):
pass
def create_html(self, tabname):
items_html = ''
for item in self.list_items():
items_html += self.create_html_for_item(item, tabname)
if items_html == '':
dirs = "".join([f"<li>{x}</li>" for x in self.allowed_directories_for_previews()])
items_html = shared.html("extra-networks-no-cards.html").format(dirs=dirs)
res = f"""
<div id='{tabname}_{self.name}_cards' class='extra-network-cards'>
{items_html}
</div>
"""
return res
def list_items(self):
raise NotImplementedError()
def allowed_directories_for_previews(self):
return []
def create_html_for_item(self, item, tabname):
preview = item.get("preview", None)
args = {
"preview_html": "style='background-image: url(" + json.dumps(preview) + ")'" if preview else '',
"prompt": item["prompt"],
"tabname": json.dumps(tabname),
"local_preview": json.dumps(item["local_preview"]),
"name": item["name"],
"allow_negative_prompt": "true" if self.allow_negative_prompt else "false",
}
return self.card_page.format(**args)
def intialize():
extra_pages.clear()
class ExtraNetworksUi:
def __init__(self):
self.pages = None
self.stored_extra_pages = None
self.button_save_preview = None
self.preview_target_filename = None
self.tabname = None
def pages_in_preferred_order(pages):
tab_order = [x.lower().strip() for x in shared.opts.ui_extra_networks_tab_reorder.split(",")]
def tab_name_score(name):
name = name.lower()
for i, possible_match in enumerate(tab_order):
if possible_match in name:
return i
return len(pages)
tab_scores = {page.name: (tab_name_score(page.name), original_index) for original_index, page in enumerate(pages)}
return sorted(pages, key=lambda x: tab_scores[x.name])
def create_ui(container, button, tabname):
ui = ExtraNetworksUi()
ui.pages = []
ui.stored_extra_pages = pages_in_preferred_order(extra_pages.copy())
ui.tabname = tabname
with gr.Tabs(elem_id=tabname+"_extra_tabs") as tabs:
for page in ui.stored_extra_pages:
with gr.Tab(page.title):
page_elem = gr.HTML(page.create_html(ui.tabname))
ui.pages.append(page_elem)
filter = gr.Textbox('', show_label=False, elem_id=tabname+"_extra_search", placeholder="Search...", visible=False)
button_refresh = gr.Button('Refresh', elem_id=tabname+"_extra_refresh")
button_close = gr.Button('Close', elem_id=tabname+"_extra_close")
ui.button_save_preview = gr.Button('Save preview', elem_id=tabname+"_save_preview", visible=False)
ui.preview_target_filename = gr.Textbox('Preview save filename', elem_id=tabname+"_preview_filename", visible=False)
button.click(fn=lambda: gr.update(visible=True), inputs=[], outputs=[container])
button_close.click(fn=lambda: gr.update(visible=False), inputs=[], outputs=[container])
def refresh():
res = []
for pg in ui.stored_extra_pages:
pg.refresh()
res.append(pg.create_html(ui.tabname))
return res
button_refresh.click(fn=refresh, inputs=[], outputs=ui.pages)
return ui
def path_is_parent(parent_path, child_path):
parent_path = os.path.abspath(parent_path)
child_path = os.path.abspath(child_path)
return os.path.commonpath([parent_path]) == os.path.commonpath([parent_path, child_path])
def setup_ui(ui, gallery):
def save_preview(index, images, filename):
if len(images) == 0:
print("There is no image in gallery to save as a preview.")
return [page.create_html(ui.tabname) for page in ui.stored_extra_pages]
index = int(index)
index = 0 if index < 0 else index
index = len(images) - 1 if index >= len(images) else index
img_info = images[index if index >= 0 else 0]
image = image_from_url_text(img_info)
is_allowed = False
for extra_page in ui.stored_extra_pages:
if any([path_is_parent(x, filename) for x in extra_page.allowed_directories_for_previews()]):
is_allowed = True
break
assert is_allowed, f'writing to {filename} is not allowed'
image.save(filename)
return [page.create_html(ui.tabname) for page in ui.stored_extra_pages]
ui.button_save_preview.click(
fn=save_preview,
_js="function(x, y, z){console.log(x, y, z); return [selected_gallery_index(), y, z]}",
inputs=[ui.preview_target_filename, gallery, ui.preview_target_filename],
outputs=[*ui.pages]
)

35
modules/ui_extra_networks_hypernets.py Normal file
View File

@ -0,0 +1,35 @@
import json
import os
from modules import shared, ui_extra_networks
class ExtraNetworksPageHypernetworks(ui_extra_networks.ExtraNetworksPage):
def __init__(self):
super().__init__('Hypernetworks')
def refresh(self):
shared.reload_hypernetworks()
def list_items(self):
for name, path in shared.hypernetworks.items():
path, ext = os.path.splitext(path)
previews = [path + ".png", path + ".preview.png"]
preview = None
for file in previews:
if os.path.isfile(file):
preview = "./file=" + file.replace('\\', '/') + "?mtime=" + str(os.path.getmtime(file))
break
yield {
"name": name,
"filename": path,
"preview": preview,
"prompt": json.dumps(f"<hypernet:{name}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
"local_preview": path + ".png",
}
def allowed_directories_for_previews(self):
return [shared.cmd_opts.hypernetwork_dir]

33
modules/ui_extra_networks_textual_inversion.py Normal file
View File

@ -0,0 +1,33 @@
import json
import os
from modules import ui_extra_networks, sd_hijack
class ExtraNetworksPageTextualInversion(ui_extra_networks.ExtraNetworksPage):
def __init__(self):
super().__init__('Textual Inversion')
self.allow_negative_prompt = True
def refresh(self):
sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True)
def list_items(self):
for embedding in sd_hijack.model_hijack.embedding_db.word_embeddings.values():
path, ext = os.path.splitext(embedding.filename)
preview_file = path + ".preview.png"
preview = None
if os.path.isfile(preview_file):
preview = "./file=" + preview_file.replace('\\', '/') + "?mtime=" + str(os.path.getmtime(preview_file))
yield {
"name": embedding.name,
"filename": embedding.filename,
"preview": preview,
"prompt": json.dumps(embedding.name),
"local_preview": path + ".preview.png",
}
def allowed_directories_for_previews(self):
return list(sd_hijack.model_hijack.embedding_db.embedding_dirs)

101
modules/ui_progress.py
View File

@ -1,101 +0,0 @@
import time
import gradio as gr
from modules.shared import opts
import modules.shared as shared
def calc_time_left(progress, threshold, label, force_display, show_eta):
if progress == 0:
return ""
else:
time_since_start = time.time() - shared.state.time_start
eta = (time_since_start/progress)
eta_relative = eta-time_since_start
if (eta_relative > threshold and show_eta) or force_display:
if eta_relative > 3600:
return label + time.strftime('%H:%M:%S', time.gmtime(eta_relative))
elif eta_relative > 60:
return label + time.strftime('%M:%S', time.gmtime(eta_relative))
else:
return label + time.strftime('%Ss', time.gmtime(eta_relative))
else:
return ""
def check_progress_call(id_part):
if shared.state.job_count == 0:
return "", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
progress = 0
if shared.state.job_count > 0:
progress += shared.state.job_no / shared.state.job_count
if shared.state.sampling_steps > 0:
progress += 1 / shared.state.job_count * shared.state.sampling_step / shared.state.sampling_steps
# Show progress percentage and time left at the same moment, and base it also on steps done
show_eta = progress >= 0.01 or shared.state.sampling_step >= 10
time_left = calc_time_left(progress, 1, " ETA: ", shared.state.time_left_force_display, show_eta)
if time_left != "":
shared.state.time_left_force_display = True
progress = min(progress, 1)
progressbar = ""
if opts.show_progressbar:
progressbar = f"""<div class='progressDiv'><div class='progress' style="overflow:visible;width:{progress * 100}%;white-space:nowrap;">{"&nbsp;" * 2 + str(int(progress*100))+"%" + time_left if show_eta else ""}</div></div>"""
image = gr.update(visible=False)
preview_visibility = gr.update(visible=False)
if opts.live_previews_enable:
shared.state.set_current_image()
image = shared.state.current_image
if image is None:
image = gr.update(value=None)
else:
preview_visibility = gr.update(visible=True)
if shared.state.textinfo is not None:
textinfo_result = gr.HTML.update(value=shared.state.textinfo, visible=True)
else:
textinfo_result = gr.update(visible=False)
return f"<span id='{id_part}_progress_span' style='display: none'>{time.time()}</span><p>{progressbar}</p>", preview_visibility, image, textinfo_result
def check_progress_call_initial(id_part):
shared.state.job_count = -1
shared.state.current_latent = None
shared.state.current_image = None
shared.state.textinfo = None
shared.state.time_start = time.time()
shared.state.time_left_force_display = False
return check_progress_call(id_part)
def setup_progressbar(progressbar, preview, id_part, textinfo=None):
if textinfo is None:
textinfo = gr.HTML(visible=False)
check_progress = gr.Button('Check progress', elem_id=f"{id_part}_check_progress", visible=False)
check_progress.click(
fn=lambda: check_progress_call(id_part),
show_progress=False,
inputs=[],
outputs=[progressbar, preview, preview, textinfo],
)
check_progress_initial = gr.Button('Check progress (first)', elem_id=f"{id_part}_check_progress_initial", visible=False)
check_progress_initial.click(
fn=lambda: check_progress_call_initial(id_part),
show_progress=False,
inputs=[],
outputs=[progressbar, preview, preview, textinfo],
)

1
modules/upscaler.py
View File

@ -95,6 +95,7 @@ class UpscalerData:
def __init__(self, name: str, path: str, upscaler: Upscaler = None, scale: int = 4, model=None):
self.name = name
self.data_path = path
self.local_data_path = path
self.scaler = upscaler
self.scale = scale
self.model = model

2
requirements.txt
View File

@ -5,7 +5,7 @@ fairscale==0.4.4
fonts
font-roboto
gfpgan
gradio==3.15.0
gradio==3.16.2
invisible-watermark
numpy
omegaconf

2
requirements_versions.txt
View File

@ -3,7 +3,7 @@ transformers==4.19.2
accelerate==0.12.0
basicsr==1.4.2
gfpgan==1.3.8
gradio==3.15.0
gradio==3.16.2
numpy==1.23.3
Pillow==9.4.0
realesrgan==0.3.0

13
script.js
View File

@ -13,6 +13,7 @@ function get_uiCurrentTabContent() {
}
uiUpdateCallbacks = []
uiLoadedCallbacks = []
uiTabChangeCallbacks = []
optionsChangedCallbacks = []
let uiCurrentTab = null
@ -20,6 +21,9 @@ let uiCurrentTab = null
function onUiUpdate(callback){
uiUpdateCallbacks.push(callback)
}
function onUiLoaded(callback){
uiLoadedCallbacks.push(callback)
}
function onUiTabChange(callback){
uiTabChangeCallbacks.push(callback)
}
@ -38,8 +42,15 @@ function executeCallbacks(queue, m) {
queue.forEach(function(x){runCallback(x, m)})
}
var executedOnLoaded = false;
document.addEventListener("DOMContentLoaded", function() {
var mutationObserver = new MutationObserver(function(m){
if(!executedOnLoaded && gradioApp().querySelector('#txt2img_prompt')){
executedOnLoaded = true;
executeCallbacks(uiLoadedCallbacks);
}
executeCallbacks(uiUpdateCallbacks, m);
const newTab = get_uiCurrentTab();
if ( newTab && ( newTab !== uiCurrentTab ) ) {
@ -53,7 +64,7 @@ document.addEventListener("DOMContentLoaded", function() {
/**
* Add a ctrl+enter as a shortcut to start a generation
*/
document.addEventListener('keydown', function(e) {
document.addEventListener('keydown', function(e) {
var handled = false;
if (e.key !== undefined) {
if((e.key == "Enter" && (e.metaKey || e.ctrlKey || e.altKey))) handled = true;

2
scripts/prompts_from_file.py
View File

@ -116,7 +116,7 @@ class Script(scripts.Script):
checkbox_iterate_batch = gr.Checkbox(label="Use same random seed for all lines", value=False, elem_id=self.elem_id("checkbox_iterate_batch"))
prompt_txt = gr.Textbox(label="List of prompt inputs", lines=1, elem_id=self.elem_id("prompt_txt"))
file = gr.File(label="Upload prompt inputs", type='bytes', elem_id=self.elem_id("file"))
file = gr.File(label="Upload prompt inputs", type='binary', elem_id=self.elem_id("file"))
file.change(fn=load_prompt_file, inputs=[file], outputs=[file, prompt_txt, prompt_txt])

235
scripts/xy_grid.py
View File

@ -10,8 +10,7 @@ import numpy as np
import modules.scripts as scripts
import gradio as gr
from modules import images, paths, sd_samplers, processing
from modules.hypernetworks import hypernetwork
from modules import images, paths, sd_samplers, processing, sd_models, sd_vae
from modules.processing import process_images, Processed, StableDiffusionProcessingTxt2Img
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
@ -22,6 +21,10 @@ import glob
import os
import re
from modules.ui_components import ToolButton
fill_values_symbol = "\U0001f4d2" # 📒
def apply_field(field):
def fun(p, x, xs):
@ -82,7 +85,6 @@ def apply_checkpoint(p, x, xs):
if info is None:
raise RuntimeError(f"Unknown checkpoint: {x}")
modules.sd_models.reload_model_weights(shared.sd_model, info)
p.sd_model = shared.sd_model
def confirm_checkpoints(p, xs):
@ -91,28 +93,6 @@ def confirm_checkpoints(p, xs):
raise RuntimeError(f"Unknown checkpoint: {x}")
def apply_hypernetwork(p, x, xs):
if x.lower() in ["", "none"]:
name = None
else:
name = hypernetwork.find_closest_hypernetwork_name(x)
if not name:
raise RuntimeError(f"Unknown hypernetwork: {x}")
hypernetwork.load_hypernetwork(name)
def apply_hypernetwork_strength(p, x, xs):
hypernetwork.apply_strength(x)
def confirm_hypernetworks(p, xs):
for x in xs:
if x.lower() in ["", "none"]:
continue
if not hypernetwork.find_closest_hypernetwork_name(x):
raise RuntimeError(f"Unknown hypernetwork: {x}")
def apply_clip_skip(p, x, xs):
opts.data["CLIP_stop_at_last_layers"] = x
@ -175,80 +155,109 @@ def str_permutations(x):
"""dummy function for specifying it in AxisOption's type when you want to get a list of permutations"""
return x
AxisOption = namedtuple("AxisOption", ["label", "type", "apply", "format_value", "confirm"])
AxisOptionImg2Img = namedtuple("AxisOptionImg2Img", ["label", "type", "apply", "format_value", "confirm"])
class AxisOption:
def __init__(self, label, type, apply, format_value=format_value_add_label, confirm=None, cost=0.0, choices=None):
self.label = label
self.type = type
self.apply = apply
self.format_value = format_value
self.confirm = confirm
self.cost = cost
self.choices = choices
class AxisOptionImg2Img(AxisOption):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.is_img2img = True
class AxisOptionTxt2Img(AxisOption):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.is_img2img = False
axis_options = [
AxisOption("Nothing", str, do_nothing, format_nothing, None),
AxisOption("Seed", int, apply_field("seed"), format_value_add_label, None),
AxisOption("Var. seed", int, apply_field("subseed"), format_value_add_label, None),
AxisOption("Var. strength", float, apply_field("subseed_strength"), format_value_add_label, None),
AxisOption("Steps", int, apply_field("steps"), format_value_add_label, None),
AxisOption("CFG Scale", float, apply_field("cfg_scale"), format_value_add_label, None),
AxisOption("Prompt S/R", str, apply_prompt, format_value, None),
AxisOption("Prompt order", str_permutations, apply_order, format_value_join_list, None),
AxisOption("Sampler", str, apply_sampler, format_value, confirm_samplers),
AxisOption("Checkpoint name", str, apply_checkpoint, format_value, confirm_checkpoints),
AxisOption("Hypernetwork", str, apply_hypernetwork, format_value, confirm_hypernetworks),
AxisOption("Hypernet str.", float, apply_hypernetwork_strength, format_value_add_label, None),
AxisOption("Sigma Churn", float, apply_field("s_churn"), format_value_add_label, None),
AxisOption("Sigma min", float, apply_field("s_tmin"), format_value_add_label, None),
AxisOption("Sigma max", float, apply_field("s_tmax"), format_value_add_label, None),
AxisOption("Sigma noise", float, apply_field("s_noise"), format_value_add_label, None),
AxisOption("Eta", float, apply_field("eta"), format_value_add_label, None),
AxisOption("Clip skip", int, apply_clip_skip, format_value_add_label, None),
AxisOption("Denoising", float, apply_field("denoising_strength"), format_value_add_label, None),
AxisOption("Hires upscaler", str, apply_field("hr_upscaler"), format_value_add_label, None),
AxisOption("Cond. Image Mask Weight", float, apply_field("inpainting_mask_weight"), format_value_add_label, None),
AxisOption("VAE", str, apply_vae, format_value_add_label, None),
AxisOption("Styles", str, apply_styles, format_value_add_label, None),
AxisOption("Nothing", str, do_nothing, format_value=format_nothing),
AxisOption("Seed", int, apply_field("seed")),
AxisOption("Var. seed", int, apply_field("subseed")),
AxisOption("Var. strength", float, apply_field("subseed_strength")),
AxisOption("Steps", int, apply_field("steps")),
AxisOption("CFG Scale", float, apply_field("cfg_scale")),
AxisOption("Prompt S/R", str, apply_prompt, format_value=format_value),
AxisOption("Prompt order", str_permutations, apply_order, format_value=format_value_join_list),
AxisOptionTxt2Img("Sampler", str, apply_sampler, format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers]),
AxisOptionImg2Img("Sampler", str, apply_sampler, format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers_for_img2img]),
AxisOption("Checkpoint name", str, apply_checkpoint, format_value=format_value, confirm=confirm_checkpoints, cost=1.0, choices=lambda: list(sd_models.checkpoints_list)),
AxisOption("Sigma Churn", float, apply_field("s_churn")),
AxisOption("Sigma min", float, apply_field("s_tmin")),
AxisOption("Sigma max", float, apply_field("s_tmax")),
AxisOption("Sigma noise", float, apply_field("s_noise")),
AxisOption("Eta", float, apply_field("eta")),
AxisOption("Clip skip", int, apply_clip_skip),
AxisOption("Denoising", float, apply_field("denoising_strength")),
AxisOptionTxt2Img("Hires upscaler", str, apply_field("hr_upscaler"), choices=lambda: [*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]]),
AxisOptionImg2Img("Cond. Image Mask Weight", float, apply_field("inpainting_mask_weight")),
AxisOption("VAE", str, apply_vae, cost=0.7, choices=lambda: list(sd_vae.vae_dict)),
AxisOption("Styles", str, apply_styles, choices=lambda: list(shared.prompt_styles.styles)),
]
def draw_xy_grid(p, xs, ys, x_labels, y_labels, cell, draw_legend, include_lone_images):
def draw_xy_grid(p, xs, ys, x_labels, y_labels, cell, draw_legend, include_lone_images, swap_axes_processing_order):
ver_texts = [[images.GridAnnotation(y)] for y in y_labels]
hor_texts = [[images.GridAnnotation(x)] for x in x_labels]
# Temporary list of all the images that are generated to be populated into the grid.
# Will be filled with empty images for any individual step that fails to process properly
image_cache = []
image_cache = [None] * (len(xs) * len(ys))
processed_result = None
cell_mode = "P"
cell_size = (1,1)
cell_size = (1, 1)
state.job_count = len(xs) * len(ys) * p.n_iter
for iy, y in enumerate(ys):
def process_cell(x, y, ix, iy):
nonlocal image_cache, processed_result, cell_mode, cell_size
state.job = f"{ix + iy * len(xs) + 1} out of {len(xs) * len(ys)}"
processed: Processed = cell(x, y)
try:
# this dereference will throw an exception if the image was not processed
# (this happens in cases such as if the user stops the process from the UI)
processed_image = processed.images[0]
if processed_result is None:
# Use our first valid processed result as a template container to hold our full results
processed_result = copy(processed)
cell_mode = processed_image.mode
cell_size = processed_image.size
processed_result.images = [Image.new(cell_mode, cell_size)]
image_cache[ix + iy * len(xs)] = processed_image
if include_lone_images:
processed_result.images.append(processed_image)
processed_result.all_prompts.append(processed.prompt)
processed_result.all_seeds.append(processed.seed)
processed_result.infotexts.append(processed.infotexts[0])
except:
image_cache[ix + iy * len(xs)] = Image.new(cell_mode, cell_size)
if swap_axes_processing_order:
for ix, x in enumerate(xs):
state.job = f"{ix + iy * len(xs) + 1} out of {len(xs) * len(ys)}"
processed:Processed = cell(x, y)
try:
# this dereference will throw an exception if the image was not processed
# (this happens in cases such as if the user stops the process from the UI)
processed_image = processed.images[0]
if processed_result is None:
# Use our first valid processed result as a template container to hold our full results
processed_result = copy(processed)
cell_mode = processed_image.mode
cell_size = processed_image.size
processed_result.images = [Image.new(cell_mode, cell_size)]
image_cache.append(processed_image)
if include_lone_images:
processed_result.images.append(processed_image)
processed_result.all_prompts.append(processed.prompt)
processed_result.all_seeds.append(processed.seed)
processed_result.infotexts.append(processed.infotexts[0])
except:
image_cache.append(Image.new(cell_mode, cell_size))
for iy, y in enumerate(ys):
process_cell(x, y, ix, iy)
else:
for iy, y in enumerate(ys):
for ix, x in enumerate(xs):
process_cell(x, y, ix, iy)
if not processed_result:
print("Unexpected error: draw_xy_grid failed to return even a single processed image")
return Processed()
return Processed(p, [])
grid = images.image_grid(image_cache, rows=len(ys))
if draw_legend:
@ -262,18 +271,12 @@ def draw_xy_grid(p, xs, ys, x_labels, y_labels, cell, draw_legend, include_lone_
class SharedSettingsStackHelper(object):
def __enter__(self):
self.CLIP_stop_at_last_layers = opts.CLIP_stop_at_last_layers
self.hypernetwork = opts.sd_hypernetwork
self.model = shared.sd_model
self.vae = opts.sd_vae
def __exit__(self, exc_type, exc_value, tb):
modules.sd_models.reload_model_weights(self.model)
opts.data["sd_vae"] = self.vae
modules.sd_vae.reload_vae_weights(self.model)
hypernetwork.load_hypernetwork(self.hypernetwork)
hypernetwork.apply_strength()
modules.sd_models.reload_model_weights()
modules.sd_vae.reload_vae_weights()
opts.data["CLIP_stop_at_last_layers"] = self.CLIP_stop_at_last_layers
@ -290,19 +293,44 @@ class Script(scripts.Script):
return "X/Y plot"
def ui(self, is_img2img):
current_axis_options = [x for x in axis_options if type(x) == AxisOption or type(x) == AxisOptionImg2Img and is_img2img]
self.current_axis_options = [x for x in axis_options if type(x) == AxisOption or x.is_img2img == is_img2img]
with gr.Row():
x_type = gr.Dropdown(label="X type", choices=[x.label for x in current_axis_options], value=current_axis_options[1].label, type="index", elem_id=self.elem_id("x_type"))
x_values = gr.Textbox(label="X values", lines=1, elem_id=self.elem_id("x_values"))
with gr.Column(scale=19):
with gr.Row():
x_type = gr.Dropdown(label="X type", choices=[x.label for x in self.current_axis_options], value=self.current_axis_options[1].label, type="index", elem_id=self.elem_id("x_type"))
x_values = gr.Textbox(label="X values", lines=1, elem_id=self.elem_id("x_values"))
fill_x_button = ToolButton(value=fill_values_symbol, elem_id="xy_grid_fill_x_tool_button", visible=False)
with gr.Row():
y_type = gr.Dropdown(label="Y type", choices=[x.label for x in current_axis_options], value=current_axis_options[0].label, type="index", elem_id=self.elem_id("y_type"))
y_values = gr.Textbox(label="Y values", lines=1, elem_id=self.elem_id("y_values"))
draw_legend = gr.Checkbox(label='Draw legend', value=True, elem_id=self.elem_id("draw_legend"))
include_lone_images = gr.Checkbox(label='Include Separate Images', value=False, elem_id=self.elem_id("include_lone_images"))
no_fixed_seeds = gr.Checkbox(label='Keep -1 for seeds', value=False, elem_id=self.elem_id("no_fixed_seeds"))
with gr.Row():
y_type = gr.Dropdown(label="Y type", choices=[x.label for x in self.current_axis_options], value=self.current_axis_options[0].label, type="index", elem_id=self.elem_id("y_type"))
y_values = gr.Textbox(label="Y values", lines=1, elem_id=self.elem_id("y_values"))
fill_y_button = ToolButton(value=fill_values_symbol, elem_id="xy_grid_fill_y_tool_button", visible=False)
with gr.Row(variant="compact"):
draw_legend = gr.Checkbox(label='Draw legend', value=True, elem_id=self.elem_id("draw_legend"))
include_lone_images = gr.Checkbox(label='Include Separate Images', value=False, elem_id=self.elem_id("include_lone_images"))
no_fixed_seeds = gr.Checkbox(label='Keep -1 for seeds', value=False, elem_id=self.elem_id("no_fixed_seeds"))
swap_axes_button = gr.Button(value="Swap axes", elem_id="xy_grid_swap_axes_button")
def swap_axes(x_type, x_values, y_type, y_values):
return self.current_axis_options[y_type].label, y_values, self.current_axis_options[x_type].label, x_values
swap_args = [x_type, x_values, y_type, y_values]
swap_axes_button.click(swap_axes, inputs=swap_args, outputs=swap_args)
def fill(x_type):
axis = self.current_axis_options[x_type]
return ", ".join(axis.choices()) if axis.choices else gr.update()
fill_x_button.click(fn=fill, inputs=[x_type], outputs=[x_values])
fill_y_button.click(fn=fill, inputs=[y_type], outputs=[y_values])
def select_axis(x_type):
return gr.Button.update(visible=self.current_axis_options[x_type].choices is not None)
x_type.change(fn=select_axis, inputs=[x_type], outputs=[fill_x_button])
y_type.change(fn=select_axis, inputs=[y_type], outputs=[fill_y_button])
return [x_type, x_values, y_type, y_values, draw_legend, include_lone_images, no_fixed_seeds]
@ -374,10 +402,10 @@ class Script(scripts.Script):
return valslist
x_opt = axis_options[x_type]
x_opt = self.current_axis_options[x_type]
xs = process_axis(x_opt, x_values)
y_opt = axis_options[y_type]
y_opt = self.current_axis_options[y_type]
ys = process_axis(y_opt, y_values)
def fix_axis_seeds(axis_opt, axis_list):
@ -405,7 +433,15 @@ class Script(scripts.Script):
grid_infotext = [None]
# If one of the axes is very slow to change between (like SD model
# checkpoint), then make sure it is in the outer iteration of the nested
# `for` loop.
swap_axes_processing_order = x_opt.cost > y_opt.cost
def cell(x, y):
if shared.state.interrupted:
return Processed(p, [], p.seed, "")
pc = copy(p)
x_opt.apply(pc, x, xs)
y_opt.apply(pc, y, ys)
@ -440,7 +476,8 @@ class Script(scripts.Script):
y_labels=[y_opt.format_value(p, y_opt, y) for y in ys],
cell=cell,
draw_legend=draw_legend,
include_lone_images=include_lone_images
include_lone_images=include_lone_images,
swap_axes_processing_order=swap_axes_processing_order
)
if opts.grid_save:

447
style.css
View File

@ -2,12 +2,26 @@
max-width: 100%;
}
#txt2img_token_counter {
height: 0px;
.token-counter{
position: absolute;
display: inline-block;
right: 2em;
min-width: 0 !important;
width: auto;
z-index: 100;
}
#img2img_token_counter {
height: 0px;
.token-counter.error span{
box-shadow: 0 0 0.0 0.3em rgba(255,0,0,0.15), inset 0 0 0.6em rgba(255,0,0,0.075);
border: 2px solid rgba(255,0,0,0.4) !important;
}
.token-counter div{
display: inline;
}
.token-counter span{
padding: 0.1em 0.75em;
}
#sh{
@ -20,7 +34,7 @@
padding-right: 0.25em;
margin: 0.1em 0;
opacity: 0%;
cursor: default;
cursor: default;
}
.output-html p {margin: 0 0.5em;}
@ -110,29 +124,22 @@
height: 100%;
}
#roll_col{
min-width: unset !important;
flex-grow: 0 !important;
padding: 0.4em 0;
#txt2img_actions_column, #img2img_actions_column{
gap: 0;
}
#roll_col > button {
min-width: 2em;
min-height: 2em;
max-width: 2em;
max-height: 2em;
flex-grow: 0;
padding-left: 0.25em;
padding-right: 0.25em;
margin: 0.1em 0;
#txt2img_tools, #img2img_tools{
gap: 0.4em;
}
#interrogate_col{
min-width: 0 !important;
max-width: 8em !important;
margin-right: 1em;
gap: 0;
}
#interrogate, #deepbooru{
margin: 0em 0.25em 0.9em 0.25em;
margin: 0em 0.25em 0.5em 0.25em;
min-width: 8em;
max-width: 8em;
}
@ -141,8 +148,25 @@
min-width: 8em !important;
}
#txt2img_style_index, #txt2img_style2_index, #img2img_style_index, #img2img_style2_index{
margin-top: 1em;
#txt2img_styles_row, #img2img_styles_row{
gap: 0.25em;
}
#txt2img_styles_row > button, #img2img_styles_row > button{
margin: 0;
}
#txt2img_styles, #img2img_styles{
padding: 0;
}
#txt2img_styles > label > div, #img2img_styles > label > div{
min-height: 3.2em;
}
#txt2img_styles ul, #img2img_styles ul{
max-height: 35em;
z-index: 2000;
}
.gr-form{
@ -154,12 +178,6 @@
margin-bottom: 0;
}
#toprow div{
border: none;
gap: 0;
background: transparent;
}
#resize_mode{
flex: 1.5;
}
@ -221,7 +239,10 @@ fieldset span.text-gray-500, .gr-block.gr-box span.text-gray-500, label.block s
.dark fieldset span.text-gray-500, .dark .gr-block.gr-box span.text-gray-500, .dark label.block span{
background-color: rgb(31, 41, 55);
box-shadow: 6px 0 6px 0px rgb(31, 41, 55), -6px 0 6px 0px rgb(31, 41, 55);
box-shadow: none;
border: 1px solid rgba(128, 128, 128, 0.1);
border-radius: 6px;
padding: 0.1em 0.5em;
}
#txt2img_column_batch, #img2img_column_batch{
@ -286,45 +307,52 @@ input[type="range"]{
}
/* more gradio's garbage cleanup */
.min-h-\[4rem\] {
min-height: unset !important;
}
#txt2img_progressbar, #img2img_progressbar, #ti_progressbar{
position: absolute;
z-index: 1000;
right: 0;
padding-left: 5px;
padding-right: 5px;
display: block;
}
#txt2img_progress_row, #img2img_progress_row{
margin-bottom: 10px;
margin-top: -18px;
}
.min-h-\[4rem\] { min-height: unset !important; }
.min-h-\[6rem\] { min-height: unset !important; }
.progressDiv{
width: 100%;
height: 20px;
background: #b4c0cc;
border-radius: 8px;
position: absolute;
height: 20px;
top: -20px;
background: #b4c0cc;
border-radius: 3px !important;
}
.dark .progressDiv{
background: #424c5b;
background: #424c5b;
}
.progressDiv .progress{
width: 0%;
height: 20px;
background: #0060df;
color: white;
font-weight: bold;
line-height: 20px;
padding: 0 8px 0 0;
text-align: right;
border-radius: 8px;
width: 0%;
height: 20px;
background: #0060df;
color: white;
font-weight: bold;
line-height: 20px;
padding: 0 8px 0 0;
text-align: right;
border-radius: 3px;
overflow: visible;
white-space: nowrap;
padding: 0 0.5em;
}
.livePreview{
position: absolute;
z-index: 300;
background-color: white;
margin: -4px;
}
.dark .livePreview{
background-color: rgb(17 24 39 / var(--tw-bg-opacity));
}
.livePreview img{
position: absolute;
object-fit: contain;
width: 100%;
height: 100%;
}
#lightboxModal{
@ -371,7 +399,7 @@ input[type="range"]{
grid-area: tile;
}
.modalClose,
.modalClose,
.modalZoom,
.modalTileImage {
color: white;
@ -450,23 +478,25 @@ input[type="range"]{
display:none
}
#txt2img_interrupt, #img2img_interrupt{
position: absolute;
width: 50%;
height: 72px;
background: #b4c0cc;
border-radius: 0px;
display: none;
#txt2img_generate_box, #img2img_generate_box{
position: relative;
}
#txt2img_interrupt, #img2img_interrupt, #txt2img_skip, #img2img_skip{
position: absolute;
width: 50%;
height: 100%;
background: #b4c0cc;
display: none;
}
#txt2img_interrupt, #img2img_interrupt{
left: 0;
border-radius: 0.5rem 0 0 0.5rem;
}
#txt2img_skip, #img2img_skip{
position: absolute;
width: 50%;
right: 0px;
height: 72px;
background: #b4c0cc;
border-radius: 0px;
display: none;
right: 0;
border-radius: 0 0.5rem 0.5rem 0;
}
.red {
@ -508,30 +538,21 @@ input[type="range"]{
gap: 0.4em;
}
#quicksettings > div{
border: none;
background: none;
flex: unset;
gap: 1em;
}
#quicksettings > div > div{
max-width: 32em;
#quicksettings > div, #quicksettings > fieldset{
max-width: 24em;
min-width: 24em;
padding: 0;
border: none;
box-shadow: none;
background: none;
}
#quicksettings > div > div > div > div > label > span {
#quicksettings > div > div > div > label > span {
position: relative;
margin-right: 9em;
margin-bottom: -1em;
}
#quicksettings > div > div > label > span {
position: relative;
margin-bottom: -1em;
}
canvas[key="mask"] {
z-index: 12 !important;
filter: invert();
@ -617,13 +638,31 @@ canvas[key="mask"] {
background-color: rgb(31 41 55 / var(--tw-bg-opacity));
}
.gr-button-tool{
.gr-button-tool, .gr-button-tool-top{
max-width: 2.5em;
min-width: 2.5em !important;
height: 2.4em;
margin: 0.55em 0;
}
.gr-button-tool{
margin: 0.6em 0em 0.55em 0;
}
.gr-button-tool-top, #settings .gr-button-tool{
margin: 1.6em 0.7em 0.55em 0;
}
#modelmerger_results_container{
margin-top: 1em;
overflow: visible;
}
#modelmerger_models{
gap: 0;
}
#quicksettings .gr-button-tool{
margin: 0;
}
@ -666,91 +705,161 @@ footer {
font-weight: bold;
}
#txt2img_checkboxes > div > div{
#txt2img_checkboxes, #img2img_checkboxes{
margin-bottom: 0.5em;
margin-left: 0em;
}
#txt2img_checkboxes > div, #img2img_checkboxes > div{
flex: 0;
white-space: nowrap;
min-width: auto;
}
#txt2img_hires_fix{
margin-left: -0.8em;
}
.inactive{
opacity: 0.5;
}
/* The following handles localization for right-to-left (RTL) languages like Arabic.
The rtl media type will only be activated by the logic in javascript/localization.js.
If you change anything above, you need to make sure it is RTL compliant by just running
your changes through converters like https://cssjanus.github.io/ or https://rtlcss.com/.
Then, you will need to add the RTL counterpart only if needed in the rtl section below.*/
@media rtl {
/* this part was added manually */
:host {
direction: rtl;
}
select, .file-preview, .gr-text-input, .output-html:has(.performance), #ti_progress {
direction: ltr;
}
#script_list > label > select,
#x_type > label > select,
#y_type > label > select {
direction: rtl;
}
.gr-radio, .gr-checkbox{
margin-left: 0.25em;
}
[id*='_prompt_container']{
gap: 0;
}
[id*='_prompt_container'] > div{
margin: -0.4em 0 0 0;
}
.gr-compact {
border: none;
}
.dark .gr-compact{
background-color: rgb(31 41 55 / var(--tw-bg-opacity));
margin-left: 0.8em;
}
.gr-compact{
overflow: visible;
}
.gr-compact > *{
}
.gr-compact .gr-block, .gr-compact .gr-form{
border: none;
box-shadow: none;
}
.gr-compact .gr-box{
border-radius: .5rem !important;
border-width: 1px !important;
}
#mode_img2img > div > div{
gap: 0 !important;
}
[id*='img2img_copy_to_'] {
border: none;
}
[id*='img2img_copy_to_'] > button {
}
[id*='img2img_label_copy_to_'] {
font-size: 1.0em;
font-weight: bold;
text-align: center;
line-height: 2.4em;
}
.extra-networks > div > [id *= '_extra_']{
margin: 0.3em;
}
#txt2img_extra_networks .search, #img2img_extra_networks .search{
display: inline-block;
max-width: 16em;
margin: 0.3em;
}
.extra-network-cards .nocards{
margin: 1.25em 0.5em 0.5em 0.5em;
}
.extra-network-cards .nocards h1{
font-size: 1.5em;
margin-bottom: 1em;
}
.extra-network-cards .nocards li{
margin-left: 0.5em;
}
.extra-network-cards .card{
display: inline-block;
margin: 0.5em;
width: 16em;
height: 24em;
box-shadow: 0 0 5px rgba(128, 128, 128, 0.5);
border-radius: 0.2em;
position: relative;
background-size: auto 100%;
background-position: center;
overflow: hidden;
cursor: pointer;
background-image: url('./file=html/card-no-preview.png')
}
.extra-network-cards .card:hover{
box-shadow: 0 0 2px 0.3em rgba(0, 128, 255, 0.35);
}
.extra-network-cards .card .actions .additional{
display: none;
}
.extra-network-cards .card .actions{
position: absolute;
bottom: 0;
left: 0;
right: 0;
padding: 0.5em;
color: white;
background: rgba(0,0,0,0.5);
box-shadow: 0 0 0.25em 0.25em rgba(0,0,0,0.5);
text-shadow: 0 0 0.2em black;
}
.extra-network-cards .card .actions:hover{
box-shadow: 0 0 0.75em 0.75em rgba(0,0,0,0.5) !important;
}
.extra-network-cards .card .actions .name{
font-size: 1.7em;
font-weight: bold;
line-break: anywhere;
}
.extra-network-cards .card .actions:hover .additional{
display: block;
}
.extra-network-cards .card ul{
margin: 0.25em 0 0.75em 0.25em;
cursor: unset;
}
.extra-network-cards .card ul a{
cursor: pointer;
}
.extra-network-cards .card ul a:hover{
color: red;
}
/* automatically generated with few manual modifications */
.performance .time {
margin-right: unset;
margin-left: 0;
}
.justify-center.overflow-x-scroll {
justify-content: right;
}
.justify-center.overflow-x-scroll button:first-of-type {
margin-left: unset;
margin-right: auto;
}
.justify-center.overflow-x-scroll button:last-of-type {
margin-right: unset;
margin-left: auto;
}
#settings fieldset span.text-gray-500, #settings .gr-block.gr-box span.text-gray-500, #settings label.block span{
margin-right: unset;
margin-left: 8em;
}
#txt2img_progressbar, #img2img_progressbar, #ti_progressbar{
right: unset;
left: 0;
}
.progressDiv .progress{
padding: 0 0 0 8px;
text-align: left;
}
#lightboxModal{
left: unset;
right: 0;
}
.modalPrev, .modalNext{
border-radius: 3px 0 0 3px;
}
.modalNext {
right: unset;
left: 0;
border-radius: 0 3px 3px 0;
}
#imageARPreview{
left:unset;
right:0px;
}
#txt2img_skip, #img2img_skip{
right: unset;
left: 0px;
}
#context-menu{
box-shadow:-1px 1px 2px #CE6400;
}
.gr-box > div > div > input.gr-text-input{
right: unset;
left: 0.5em;
}
}

10
test/basic_features/utils_test.py
View File

@ -12,8 +12,6 @@ class UtilsTests(unittest.TestCase):
self.url_face_restorers = "http://localhost:7860/sdapi/v1/face-restorers"
self.url_realesrgan_models = "http://localhost:7860/sdapi/v1/realesrgan-models"
self.url_prompt_styles = "http://localhost:7860/sdapi/v1/prompt-styles"
self.url_artist_categories = "http://localhost:7860/sdapi/v1/artist-categories"
self.url_artists = "http://localhost:7860/sdapi/v1/artists"
self.url_embeddings = "http://localhost:7860/sdapi/v1/embeddings"
def test_options_get(self):
@ -56,15 +54,9 @@ class UtilsTests(unittest.TestCase):
def test_prompt_styles(self):
self.assertEqual(requests.get(self.url_prompt_styles).status_code, 200)
def test_artist_categories(self):
self.assertEqual(requests.get(self.url_artist_categories).status_code, 200)
def test_artists(self):
self.assertEqual(requests.get(self.url_artists).status_code, 200)
def test_embeddings(self):
self.assertEqual(requests.get(self.url_artists).status_code, 200)
self.assertEqual(requests.get(self.url_embeddings).status_code, 200)
if __name__ == "__main__":
unittest.main()

37
webui.py
View File

@ -9,16 +9,18 @@ from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from fastapi.middleware.gzip import GZipMiddleware
from modules import import_hook, errors
from modules import import_hook, errors, extra_networks
from modules import extra_networks_hypernet, ui_extra_networks_hypernets, ui_extra_networks_textual_inversion
from modules.call_queue import wrap_queued_call, queue_lock, wrap_gradio_gpu_call
from modules.paths import script_path
import torch
# Truncate version number of nightly/local build of PyTorch to not cause exceptions with CodeFormer or Safetensors
if ".dev" in torch.__version__ or "+git" in torch.__version__:
torch.__version__ = re.search(r'[\d.]+[\d]', torch.__version__).group(0)
from modules import shared, devices, sd_samplers, upscaler, extensions, localization, ui_tempdir
from modules import shared, devices, sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks
import modules.codeformer_model as codeformer
import modules.extras
import modules.face_restoration
@ -34,6 +36,7 @@ import modules.sd_vae
import modules.txt2img
import modules.script_callbacks
import modules.textual_inversion.textual_inversion
import modules.progress
import modules.ui
from modules import modelloader
@ -83,10 +86,17 @@ def initialize():
shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights()))
shared.opts.onchange("sd_vae", wrap_queued_call(lambda: modules.sd_vae.reload_vae_weights()), call=False)
shared.opts.onchange("sd_vae_as_default", wrap_queued_call(lambda: modules.sd_vae.reload_vae_weights()), call=False)
shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: shared.reload_hypernetworks()))
shared.opts.onchange("sd_hypernetwork_strength", modules.hypernetworks.hypernetwork.apply_strength)
shared.opts.onchange("temp_dir", ui_tempdir.on_tmpdir_changed)
shared.reload_hypernetworks()
ui_extra_networks.intialize()
ui_extra_networks.register_page(ui_extra_networks_textual_inversion.ExtraNetworksPageTextualInversion())
ui_extra_networks.register_page(ui_extra_networks_hypernets.ExtraNetworksPageHypernetworks())
extra_networks.initialize()
extra_networks.register_extra_network(extra_networks_hypernet.ExtraNetworkHypernet())
if cmd_opts.tls_keyfile is not None and cmd_opts.tls_keyfile is not None:
try:
@ -155,9 +165,14 @@ def webui():
if shared.opts.clean_temp_dir_at_start:
ui_tempdir.cleanup_tmpdr()
modules.script_callbacks.before_ui_callback()
shared.demo = modules.ui.create_ui()
app, local_url, share_url = shared.demo.queue(default_enabled=False).launch(
if cmd_opts.gradio_queue:
shared.demo.queue(64)
app, local_url, share_url = shared.demo.launch(
share=cmd_opts.share,
server_name=server_name,
server_port=cmd_opts.port,
@ -181,11 +196,12 @@ def webui():
app.add_middleware(GZipMiddleware, minimum_size=1000)
modules.progress.setup_progress_api(app)
if launch_api:
create_api(app)
modules.script_callbacks.app_started_callback(shared.demo, app)
modules.script_callbacks.app_started_callback(shared.demo, app)
wait_on_server(shared.demo)
print('Restarting UI...')
@ -207,6 +223,15 @@ def webui():
modules.sd_models.list_models()
shared.reload_hypernetworks()
ui_extra_networks.intialize()
ui_extra_networks.register_page(ui_extra_networks_textual_inversion.ExtraNetworksPageTextualInversion())
ui_extra_networks.register_page(ui_extra_networks_hypernets.ExtraNetworksPageHypernetworks())
extra_networks.initialize()
extra_networks.register_extra_network(extra_networks_hypernet.ExtraNetworkHypernet())
if __name__ == "__main__":
if cmd_opts.nowebui:

19
webui.sh
View File

@ -104,6 +104,23 @@ then
fi
# Check prerequisites
gpu_info=$(lspci 2>/dev/null | grep VGA)
case "$gpu_info" in
*"Navi 1"*|*"Navi 2"*) export HSA_OVERRIDE_GFX_VERSION=10.3.0
;;
*"Renoir"*) export HSA_OVERRIDE_GFX_VERSION=9.0.0
printf "\n%s\n" "${delimiter}"
printf "Experimental support for Renoir: make sure to have at least 4GB of VRAM and 10GB of RAM or enable cpu mode: --use-cpu all --no-half"
printf "\n%s\n" "${delimiter}"
;;
*)
;;
esac
if echo "$gpu_info" | grep -q "AMD" && [[ -z "${TORCH_COMMAND}" ]]
then
export TORCH_COMMAND="pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/rocm5.2"
fi
for preq in "${GIT}" "${python_cmd}"
do
if ! hash "${preq}" &>/dev/null
@ -164,6 +181,6 @@ then
else
printf "\n%s\n" "${delimiter}"
printf "Launching launch.py..."
printf "\n%s\n" "${delimiter}"
printf "\n%s\n" "${delimiter}"
exec "${python_cmd}" "${LAUNCH_SCRIPT}" "$@"
fi