diff --git a/modules/api/api.py b/modules/api/api.py
index 2a43085f..112000b8 100644
--- a/modules/api/api.py
+++ b/modules/api/api.py
@@ -231,6 +231,10 @@ class Api:
return options
def set_config(self, req: OptionsModel):
+ # currently req has all options fields even if you send a dict like { "send_seed": false }, which means it will
+ # overwrite all options with default values.
+ raise RuntimeError('Setting options via API is not supported')
+
reqDict = vars(req)
for o in reqDict:
setattr(shared.opts, o, reqDict[o])
diff --git a/modules/api/models.py b/modules/api/models.py
index 2ae75f43..a44c5ddd 100644
--- a/modules/api/models.py
+++ b/modules/api/models.py
@@ -1,6 +1,6 @@
import inspect
from pydantic import BaseModel, Field, create_model
-from typing import Any, Optional, Union
+from typing import Any, Optional
from typing_extensions import Literal
from inflection import underscore
from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
@@ -185,22 +185,22 @@ _options = vars(parser)['_option_string_actions']
for key in _options:
if(_options[key].dest != 'help'):
flag = _options[key]
- _type = str
- if(_options[key].default != None): _type = type(_options[key].default)
+ _type = str
+ if _options[key].default is not None: _type = type(_options[key].default)
flags.update({flag.dest: (_type,Field(default=flag.default, description=flag.help))})
FlagsModel = create_model("Flags", **flags)
class SamplerItem(BaseModel):
name: str = Field(title="Name")
- aliases: list[str] = Field(title="Aliases")
+ aliases: list[str] = Field(title="Aliases")
options: dict[str, str] = Field(title="Options")
class UpscalerItem(BaseModel):
name: str = Field(title="Name")
- model_name: str | None = Field(title="Model Name")
- model_path: str | None = Field(title="Path")
- model_url: str | None = Field(title="URL")
+ model_name: Optional[str] = Field(title="Model Name")
+ model_path: Optional[str] = Field(title="Path")
+ model_url: Optional[str] = Field(title="URL")
class SDModelItem(BaseModel):
title: str = Field(title="Title")
@@ -211,21 +211,21 @@ class SDModelItem(BaseModel):
class HypernetworkItem(BaseModel):
name: str = Field(title="Name")
- path: str | None = Field(title="Path")
+ path: Optional[str] = Field(title="Path")
class FaceRestorerItem(BaseModel):
name: str = Field(title="Name")
- cmd_dir: str | None = Field(title="Path")
+ cmd_dir: Optional[str] = Field(title="Path")
class RealesrganItem(BaseModel):
name: str = Field(title="Name")
- path: str | None = Field(title="Path")
- scale: int | None = Field(title="Scale")
+ path: Optional[str] = Field(title="Path")
+ scale: Optional[int] = Field(title="Scale")
class PromptStyleItem(BaseModel):
name: str = Field(title="Name")
- prompt: str | None = Field(title="Prompt")
- negative_prompt: str | None = Field(title="Negative Prompt")
+ prompt: Optional[str] = Field(title="Prompt")
+ negative_prompt: Optional[str] = Field(title="Negative Prompt")
class ArtistItem(BaseModel):
name: str = Field(title="Name")
diff --git a/modules/extensions.py b/modules/extensions.py
index 897af96e..8e0977fd 100644
--- a/modules/extensions.py
+++ b/modules/extensions.py
@@ -34,8 +34,11 @@ class Extension:
if repo is None or repo.bare:
self.remote = None
else:
- self.remote = next(repo.remote().urls, None)
- self.status = 'unknown'
+ try:
+ self.remote = next(repo.remote().urls, None)
+ self.status = 'unknown'
+ except Exception:
+ self.remote = None
def list_files(self, subdir, extension):
from modules import scripts
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py
index 6e1a10cf..7f182712 100644
--- a/modules/hypernetworks/hypernetwork.py
+++ b/modules/hypernetworks/hypernetwork.py
@@ -22,6 +22,8 @@ from collections import defaultdict, deque
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 = {
@@ -142,6 +144,8 @@ class Hypernetwork:
self.use_dropout = use_dropout
self.activate_output = activate_output
self.last_layer_dropout = kwargs['last_layer_dropout'] if 'last_layer_dropout' in kwargs else True
+ self.optimizer_name = None
+ self.optimizer_state_dict = None
for size in enable_sizes or []:
self.layers[size] = (
@@ -163,6 +167,7 @@ class Hypernetwork:
def save(self, filename):
state_dict = {}
+ optimizer_saved_dict = {}
for k, v in self.layers.items():
state_dict[k] = (v[0].state_dict(), v[1].state_dict())
@@ -178,8 +183,15 @@ class Hypernetwork:
state_dict['sd_checkpoint_name'] = self.sd_checkpoint_name
state_dict['activate_output'] = self.activate_output
state_dict['last_layer_dropout'] = self.last_layer_dropout
-
+
+ if self.optimizer_name is not None:
+ optimizer_saved_dict['optimizer_name'] = self.optimizer_name
+
torch.save(state_dict, filename)
+ if shared.opts.save_optimizer_state and self.optimizer_state_dict:
+ optimizer_saved_dict['hash'] = sd_models.model_hash(filename)
+ optimizer_saved_dict['optimizer_state_dict'] = self.optimizer_state_dict
+ torch.save(optimizer_saved_dict, filename + '.optim')
def load(self, filename):
self.filename = filename
@@ -202,6 +214,18 @@ class Hypernetwork:
print(f"Activate last layer is set to {self.activate_output}")
self.last_layer_dropout = state_dict.get('last_layer_dropout', False)
+ optimizer_saved_dict = torch.load(self.filename + '.optim', map_location = 'cpu') if os.path.exists(self.filename + '.optim') else {}
+ self.optimizer_name = optimizer_saved_dict.get('optimizer_name', 'AdamW')
+ print(f"Optimizer name is {self.optimizer_name}")
+ if sd_models.model_hash(filename) == optimizer_saved_dict.get('hash', None):
+ self.optimizer_state_dict = optimizer_saved_dict.get('optimizer_state_dict', None)
+ else:
+ self.optimizer_state_dict = None
+ if self.optimizer_state_dict:
+ print("Loaded existing optimizer from checkpoint")
+ else:
+ print("No saved optimizer exists in checkpoint")
+
for size, sd in state_dict.items():
if type(size) == int:
self.layers[size] = (
@@ -219,11 +243,11 @@ class Hypernetwork:
def list_hypernetworks(path):
res = {}
- for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
+ for filename in sorted(glob.iglob(os.path.join(path, '**/*.pt'), recursive=True)):
name = os.path.splitext(os.path.basename(filename))[0]
# Prevent a hypothetical "None.pt" from being listed.
if name != "None":
- res[name] = filename
+ res[name + f"({sd_models.model_hash(filename)})"] = filename
return res
@@ -358,6 +382,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
shared.state.textinfo = "Initializing hypernetwork training..."
shared.state.job_count = steps
+ hypernetwork_name = hypernetwork_name.rsplit('(', 1)[0]
filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt')
log_directory = os.path.join(log_directory, datetime.datetime.now().strftime("%Y-%m-%d"), hypernetwork_name)
@@ -404,8 +429,22 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
weights = hypernetwork.weights()
for weight in weights:
weight.requires_grad = True
- # if optimizer == "AdamW": or else Adam / AdamW / SGD, etc...
- optimizer = torch.optim.AdamW(weights, lr=scheduler.learn_rate)
+
+ # Here we use optimizer from saved HN, or we can specify as UI option.
+ if hypernetwork.optimizer_name in optimizer_dict:
+ optimizer = optimizer_dict[hypernetwork.optimizer_name](params=weights, lr=scheduler.learn_rate)
+ optimizer_name = hypernetwork.optimizer_name
+ else:
+ print(f"Optimizer type {hypernetwork.optimizer_name} is not defined!")
+ optimizer = torch.optim.AdamW(params=weights, lr=scheduler.learn_rate)
+ optimizer_name = 'AdamW'
+
+ if hypernetwork.optimizer_state_dict: # This line must be changed if Optimizer type can be different from saved optimizer.
+ try:
+ optimizer.load_state_dict(hypernetwork.optimizer_state_dict)
+ except RuntimeError as e:
+ print("Cannot resume from saved optimizer!")
+ print(e)
steps_without_grad = 0
@@ -467,7 +506,11 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
# Before saving, change name to match current checkpoint.
hypernetwork_name_every = f'{hypernetwork_name}-{steps_done}'
last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name_every}.pt')
+ hypernetwork.optimizer_name = optimizer_name
+ if shared.opts.save_optimizer_state:
+ hypernetwork.optimizer_state_dict = optimizer.state_dict()
save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, last_saved_file)
+ hypernetwork.optimizer_state_dict = None # dereference it after saving, to save memory.
textual_inversion.write_loss(log_directory, "hypernetwork_loss.csv", hypernetwork.step, len(ds), {
"loss": f"{previous_mean_loss:.7f}",
@@ -530,8 +573,12 @@ Last saved image: {html.escape(last_saved_image)}
report_statistics(loss_dict)
filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt')
+ hypernetwork.optimizer_name = optimizer_name
+ if shared.opts.save_optimizer_state:
+ hypernetwork.optimizer_state_dict = optimizer.state_dict()
save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, filename)
-
+ del optimizer
+ hypernetwork.optimizer_state_dict = None # dereference it after saving, to save memory.
return hypernetwork, filename
def save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, filename):
diff --git a/modules/hypernetworks/ui.py b/modules/hypernetworks/ui.py
index aad09ffc..c2d4b51c 100644
--- a/modules/hypernetworks/ui.py
+++ b/modules/hypernetworks/ui.py
@@ -9,7 +9,7 @@ from modules import devices, sd_hijack, shared
from modules.hypernetworks import hypernetwork
not_available = ["hardswish", "multiheadattention"]
-keys = ["linear"] + list(x for x in hypernetwork.HypernetworkModule.activation_dict.keys() if x not in not_available)
+keys = list(x for x in 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):
# Remove illegal characters from name.
diff --git a/modules/shared.py b/modules/shared.py
index a9e28b9c..70b998ff 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -86,6 +86,10 @@ parser.add_argument("--nowebui", action='store_true', help="use api=True to laun
parser.add_argument("--ui-debug-mode", action='store_true', help="Don't load model to quickly launch UI")
parser.add_argument("--device-id", type=str, help="Select the default CUDA device to use (export CUDA_VISIBLE_DEVICES=0,1,etc might be needed before)", default=None)
parser.add_argument("--administrator", action='store_true', help="Administrator rights", default=False)
+parser.add_argument("--cors-allow-origins", type=str, help="Allowed CORS origins", default=None)
+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)
cmd_opts = parser.parse_args()
restricted_opts = {
@@ -147,9 +151,9 @@ class State:
self.interrupted = True
def nextjob(self):
- if opts.show_progress_every_n_steps == -1:
+ if opts.show_progress_every_n_steps == -1:
self.do_set_current_image()
-
+
self.job_no += 1
self.sampling_step = 0
self.current_image_sampling_step = 0
@@ -198,7 +202,7 @@ class State:
return
if self.current_latent is None:
return
-
+
if opts.show_progress_grid:
self.current_image = sd_samplers.samples_to_image_grid(self.current_latent)
else:
@@ -317,6 +321,7 @@ options_templates.update(options_section(('system', "System"), {
options_templates.update(options_section(('training', "Training"), {
"unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training if possible. Saves VRAM."),
+ "save_optimizer_state": OptionInfo(False, "Saves Optimizer state as separate *.optim file. Training can be resumed with HN itself and matching optim file."),
"dataset_filename_word_regex": OptionInfo("", "Filename word regex"),
"dataset_filename_join_string": OptionInfo(" ", "Filename join string"),
"training_image_repeats_per_epoch": OptionInfo(1, "Number of repeats for a single input image per epoch; used only for displaying epoch number", gr.Number, {"precision": 0}),
@@ -406,7 +411,8 @@ class Options:
if key in self.data or key in self.data_labels:
assert not cmd_opts.freeze_settings, "changing settings is disabled"
- comp_args = opts.data_labels[key].component_args
+ info = opts.data_labels.get(key, None)
+ comp_args = info.component_args if info else None
if isinstance(comp_args, dict) and comp_args.get('visible', True) is False:
raise RuntimeError(f"not possible to set {key} because it is restricted")
diff --git a/modules/ui.py b/modules/ui.py
index 4c2829af..76ca9b07 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1446,17 +1446,19 @@ def create_ui(wrap_gradio_gpu_call):
continue
oldval = opts.data.get(key, None)
-
- setattr(opts, key, value)
-
+ try:
+ setattr(opts, key, value)
+ except RuntimeError:
+ continue
if oldval != value:
if opts.data_labels[key].onchange is not None:
opts.data_labels[key].onchange()
changed += 1
-
- opts.save(shared.config_filename)
-
+ try:
+ opts.save(shared.config_filename)
+ except RuntimeError:
+ return opts.dumpjson(), f'{changed} settings changed without save.'
return opts.dumpjson(), f'{changed} settings changed.'
def run_settings_single(value, key):
diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py
index a81de9a7..8e0d41d5 100644
--- a/modules/ui_extensions.py
+++ b/modules/ui_extensions.py
@@ -188,7 +188,7 @@ def refresh_available_extensions_from_data():
code += f"""