Merge branch 'master' of https://github.com/anapnoe/stable-diffusion-webui
This commit is contained in:
anapnoe
commit
69b638e39b
|
|
@ -1,22 +1,17 @@
|
|||
import sys, os, shlex
|
||||
import sys
|
||||
import contextlib
|
||||
import torch
|
||||
from modules import errors
|
||||
from modules.sd_hijack_utils import CondFunc
|
||||
from packaging import version
|
||||
|
||||
if sys.platform == "darwin":
|
||||
from modules import mac_specific
|
||||
|
||||
|
||||
# has_mps is only available in nightly pytorch (for now) and macOS 12.3+.
|
||||
# check `getattr` and try it for compatibility
|
||||
def has_mps() -> bool:
|
||||
if not getattr(torch, 'has_mps', False):
|
||||
if sys.platform != "darwin":
|
||||
return False
|
||||
try:
|
||||
torch.zeros(1).to(torch.device("mps"))
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
else:
|
||||
return mac_specific.has_mps
|
||||
|
||||
def extract_device_id(args, name):
|
||||
for x in range(len(args)):
|
||||
|
|
@ -155,36 +150,3 @@ def test_for_nans(x, where):
|
|||
message += " Use --disable-nan-check commandline argument to disable this check."
|
||||
|
||||
raise NansException(message)
|
||||
|
||||
|
||||
# MPS workaround for https://github.com/pytorch/pytorch/issues/89784
|
||||
def cumsum_fix(input, cumsum_func, *args, **kwargs):
|
||||
if input.device.type == 'mps':
|
||||
output_dtype = kwargs.get('dtype', input.dtype)
|
||||
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)
|
||||
|
||||
|
||||
if has_mps():
|
||||
if version.parse(torch.__version__) < version.parse("1.13"):
|
||||
# PyTorch 1.13 doesn't need these fixes but unfortunately is slower and has regressions that prevent training from working
|
||||
|
||||
# MPS workaround for https://github.com/pytorch/pytorch/issues/79383
|
||||
CondFunc('torch.Tensor.to', lambda orig_func, self, *args, **kwargs: orig_func(self.contiguous(), *args, **kwargs),
|
||||
lambda _, self, *args, **kwargs: self.device.type != 'mps' and (args and isinstance(args[0], torch.device) and args[0].type == 'mps' or isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps'))
|
||||
# MPS workaround for https://github.com/pytorch/pytorch/issues/80800
|
||||
CondFunc('torch.nn.functional.layer_norm', lambda orig_func, *args, **kwargs: orig_func(*([args[0].contiguous()] + list(args[1:])), **kwargs),
|
||||
lambda _, *args, **kwargs: args and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps')
|
||||
# MPS workaround for https://github.com/pytorch/pytorch/issues/90532
|
||||
CondFunc('torch.Tensor.numpy', lambda orig_func, self, *args, **kwargs: orig_func(self.detach(), *args, **kwargs), lambda _, self, *args, **kwargs: self.requires_grad)
|
||||
elif version.parse(torch.__version__) > version.parse("1.13.1"):
|
||||
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))
|
||||
cumsum_fix_func = lambda orig_func, input, *args, **kwargs: cumsum_fix(input, orig_func, *args, **kwargs)
|
||||
CondFunc('torch.cumsum', cumsum_fix_func, None)
|
||||
CondFunc('torch.Tensor.cumsum', cumsum_fix_func, None)
|
||||
CondFunc('torch.narrow', lambda orig_func, *args, **kwargs: orig_func(*args, **kwargs).clone(), None)
|
||||
|
||||
|
|
|
|||
|
|
@ -4,6 +4,7 @@ import os.path
|
|||
|
||||
import filelock
|
||||
|
||||
from modules import shared
|
||||
from modules.paths import data_path
|
||||
|
||||
|
||||
|
|
@ -68,6 +69,9 @@ def sha256(filename, title):
|
|||
if sha256_value is not None:
|
||||
return sha256_value
|
||||
|
||||
if shared.cmd_opts.no_hashing:
|
||||
return None
|
||||
|
||||
print(f"Calculating sha256 for {filename}: ", end='')
|
||||
sha256_value = calculate_sha256(filename)
|
||||
print(f"{sha256_value}")
|
||||
|
|
|
|||
|
|
@ -307,7 +307,7 @@ class Hypernetwork:
|
|||
def shorthash(self):
|
||||
sha256 = hashes.sha256(self.filename, f'hypernet/{self.name}')
|
||||
|
||||
return sha256[0:10]
|
||||
return sha256[0:10] if sha256 else None
|
||||
|
||||
|
||||
def list_hypernetworks(path):
|
||||
|
|
|
|||
|
|
@ -130,7 +130,7 @@ class GridAnnotation:
|
|||
self.size = None
|
||||
|
||||
|
||||
def draw_grid_annotations(im, width, height, hor_texts, ver_texts):
|
||||
def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
|
||||
def wrap(drawing, text, font, line_length):
|
||||
lines = ['']
|
||||
for word in text.split():
|
||||
|
|
@ -194,25 +194,28 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts):
|
|||
line.allowed_width = allowed_width
|
||||
|
||||
hor_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing for lines in hor_texts]
|
||||
ver_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing * len(lines) for lines in
|
||||
ver_texts]
|
||||
ver_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing * len(lines) for lines in ver_texts]
|
||||
|
||||
pad_top = 0 if sum(hor_text_heights) == 0 else max(hor_text_heights) + line_spacing * 2
|
||||
|
||||
result = Image.new("RGB", (im.width + pad_left, im.height + pad_top), "white")
|
||||
result.paste(im, (pad_left, pad_top))
|
||||
result = Image.new("RGB", (im.width + pad_left + margin * (rows-1), im.height + pad_top + margin * (cols-1)), "white")
|
||||
|
||||
for row in range(rows):
|
||||
for col in range(cols):
|
||||
cell = im.crop((width * col, height * row, width * (col+1), height * (row+1)))
|
||||
result.paste(cell, (pad_left + (width + margin) * col, pad_top + (height + margin) * row))
|
||||
|
||||
d = ImageDraw.Draw(result)
|
||||
|
||||
for col in range(cols):
|
||||
x = pad_left + width * col + width / 2
|
||||
x = pad_left + (width + margin) * col + width / 2
|
||||
y = pad_top / 2 - hor_text_heights[col] / 2
|
||||
|
||||
draw_texts(d, x, y, hor_texts[col], fnt, fontsize)
|
||||
|
||||
for row in range(rows):
|
||||
x = pad_left / 2
|
||||
y = pad_top + height * row + height / 2 - ver_text_heights[row] / 2
|
||||
y = pad_top + (height + margin) * row + height / 2 - ver_text_heights[row] / 2
|
||||
|
||||
draw_texts(d, x, y, ver_texts[row], fnt, fontsize)
|
||||
|
||||
|
|
|
|||
53
modules/mac_specific.py
Normal file
53
modules/mac_specific.py
Normal file
|
|
@ -0,0 +1,53 @@
|
|||
import torch
|
||||
from modules import paths
|
||||
from modules.sd_hijack_utils import CondFunc
|
||||
from packaging import version
|
||||
|
||||
|
||||
# has_mps is only available in nightly pytorch (for now) and macOS 12.3+.
|
||||
# check `getattr` and try it for compatibility
|
||||
def check_for_mps() -> bool:
|
||||
if not getattr(torch, 'has_mps', False):
|
||||
return False
|
||||
try:
|
||||
torch.zeros(1).to(torch.device("mps"))
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
has_mps = check_for_mps()
|
||||
|
||||
|
||||
# MPS workaround for https://github.com/pytorch/pytorch/issues/89784
|
||||
def cumsum_fix(input, cumsum_func, *args, **kwargs):
|
||||
if input.device.type == 'mps':
|
||||
output_dtype = kwargs.get('dtype', input.dtype)
|
||||
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)
|
||||
|
||||
|
||||
if has_mps:
|
||||
# MPS fix for randn in torchsde
|
||||
CondFunc('torchsde._brownian.brownian_interval._randn', lambda _, size, dtype, device, seed: torch.randn(size, dtype=dtype, device=torch.device("cpu"), generator=torch.Generator(torch.device("cpu")).manual_seed(int(seed))).to(device), lambda _, size, dtype, device, seed: device.type == 'mps')
|
||||
|
||||
if version.parse(torch.__version__) < version.parse("1.13"):
|
||||
# PyTorch 1.13 doesn't need these fixes but unfortunately is slower and has regressions that prevent training from working
|
||||
|
||||
# MPS workaround for https://github.com/pytorch/pytorch/issues/79383
|
||||
CondFunc('torch.Tensor.to', lambda orig_func, self, *args, **kwargs: orig_func(self.contiguous(), *args, **kwargs),
|
||||
lambda _, self, *args, **kwargs: self.device.type != 'mps' and (args and isinstance(args[0], torch.device) and args[0].type == 'mps' or isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps'))
|
||||
# MPS workaround for https://github.com/pytorch/pytorch/issues/80800
|
||||
CondFunc('torch.nn.functional.layer_norm', lambda orig_func, *args, **kwargs: orig_func(*([args[0].contiguous()] + list(args[1:])), **kwargs),
|
||||
lambda _, *args, **kwargs: args and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps')
|
||||
# MPS workaround for https://github.com/pytorch/pytorch/issues/90532
|
||||
CondFunc('torch.Tensor.numpy', lambda orig_func, self, *args, **kwargs: orig_func(self.detach(), *args, **kwargs), lambda _, self, *args, **kwargs: self.requires_grad)
|
||||
elif version.parse(torch.__version__) > version.parse("1.13.1"):
|
||||
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))
|
||||
cumsum_fix_func = lambda orig_func, input, *args, **kwargs: cumsum_fix(input, orig_func, *args, **kwargs)
|
||||
CondFunc('torch.cumsum', cumsum_fix_func, None)
|
||||
CondFunc('torch.Tensor.cumsum', cumsum_fix_func, None)
|
||||
CondFunc('torch.narrow', lambda orig_func, *args, **kwargs: orig_func(*args, **kwargs).clone(), None)
|
||||
|
||||
|
|
@ -59,13 +59,17 @@ class CheckpointInfo:
|
|||
|
||||
def calculate_shorthash(self):
|
||||
self.sha256 = hashes.sha256(self.filename, "checkpoint/" + self.name)
|
||||
if self.sha256 is None:
|
||||
return
|
||||
|
||||
self.shorthash = self.sha256[0:10]
|
||||
|
||||
if self.shorthash not in self.ids:
|
||||
self.ids += [self.shorthash, self.sha256]
|
||||
self.register()
|
||||
self.ids += [self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]']
|
||||
|
||||
checkpoints_list.pop(self.title)
|
||||
self.title = f'{self.name} [{self.shorthash}]'
|
||||
self.register()
|
||||
|
||||
return self.shorthash
|
||||
|
||||
|
|
@ -158,7 +162,7 @@ def select_checkpoint():
|
|||
print(f" - directory {model_path}", file=sys.stderr)
|
||||
if shared.cmd_opts.ckpt_dir is not None:
|
||||
print(f" - directory {os.path.abspath(shared.cmd_opts.ckpt_dir)}", file=sys.stderr)
|
||||
print("Can't run without a checkpoint. Find and place a .ckpt file into any of those locations. The program will exit.", file=sys.stderr)
|
||||
print("Can't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. The program will exit.", file=sys.stderr)
|
||||
exit(1)
|
||||
|
||||
checkpoint_info = next(iter(checkpoints_list.values()))
|
||||
|
|
|
|||
|
|
@ -2,7 +2,6 @@ from collections import namedtuple
|
|||
import numpy as np
|
||||
import torch
|
||||
from PIL import Image
|
||||
import torchsde._brownian.brownian_interval
|
||||
from modules import devices, processing, images, sd_vae_approx
|
||||
|
||||
from modules.shared import opts, state
|
||||
|
|
@ -61,18 +60,3 @@ def store_latent(decoded):
|
|||
|
||||
class InterruptedException(BaseException):
|
||||
pass
|
||||
|
||||
|
||||
# MPS fix for randn in torchsde
|
||||
# XXX move this to separate file for MPS
|
||||
def torchsde_randn(size, dtype, device, seed):
|
||||
if device.type == 'mps':
|
||||
generator = torch.Generator(devices.cpu).manual_seed(int(seed))
|
||||
return torch.randn(size, dtype=dtype, device=devices.cpu, generator=generator).to(device)
|
||||
else:
|
||||
generator = torch.Generator(device).manual_seed(int(seed))
|
||||
return torch.randn(size, dtype=dtype, device=device, generator=generator)
|
||||
|
||||
|
||||
torchsde._brownian.brownian_interval._randn = torchsde_randn
|
||||
|
||||
|
|
|
|||
|
|
@ -41,90 +41,6 @@ sampler_extra_params = {
|
|||
'sample_dpm_2': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
|
||||
}
|
||||
|
||||
class CFGDenoiserEdit(torch.nn.Module):
|
||||
"""
|
||||
Classifier free guidance denoiser. A wrapper for stable diffusion model (specifically for unet)
|
||||
that can take a noisy picture and produce a noise-free picture using two guidances (prompts)
|
||||
instead of one. Originally, the second prompt is just an empty string, but we use non-empty
|
||||
negative prompt.
|
||||
"""
|
||||
|
||||
def __init__(self, model):
|
||||
super().__init__()
|
||||
self.inner_model = model
|
||||
self.mask = None
|
||||
self.nmask = None
|
||||
self.init_latent = None
|
||||
self.step = 0
|
||||
|
||||
def combine_denoised(self, x_out, conds_list, uncond, cond_scale, image_cfg_scale):
|
||||
denoised_uncond = x_out[-uncond.shape[0]:]
|
||||
denoised = torch.clone(denoised_uncond)
|
||||
|
||||
for i, conds in enumerate(conds_list):
|
||||
for cond_index, weight in conds:
|
||||
out_cond, out_img_cond, out_uncond = x_out.chunk(3)
|
||||
denoised[i] = out_uncond[cond_index] + cond_scale * (out_cond[cond_index] - out_img_cond[cond_index]) + image_cfg_scale * (out_img_cond[cond_index] - out_uncond[cond_index])
|
||||
|
||||
return denoised
|
||||
|
||||
def forward(self, x, sigma, uncond, cond, cond_scale, image_cond, image_cfg_scale):
|
||||
if state.interrupted or state.skipped:
|
||||
raise sd_samplers_common.InterruptedException
|
||||
|
||||
conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
|
||||
uncond = prompt_parser.reconstruct_cond_batch(uncond, self.step)
|
||||
|
||||
batch_size = len(conds_list)
|
||||
repeats = [len(conds_list[i]) for i in range(batch_size)]
|
||||
|
||||
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x] + [x])
|
||||
sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma] + [sigma])
|
||||
image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond] + [torch.zeros_like(self.init_latent)])
|
||||
|
||||
denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)
|
||||
cfg_denoiser_callback(denoiser_params)
|
||||
x_in = denoiser_params.x
|
||||
image_cond_in = denoiser_params.image_cond
|
||||
sigma_in = denoiser_params.sigma
|
||||
|
||||
if tensor.shape[1] == uncond.shape[1]:
|
||||
cond_in = torch.cat([tensor, uncond, uncond])
|
||||
|
||||
if shared.batch_cond_uncond:
|
||||
x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
|
||||
else:
|
||||
x_out = torch.zeros_like(x_in)
|
||||
for batch_offset in range(0, x_out.shape[0], batch_size):
|
||||
a = batch_offset
|
||||
b = a + batch_size
|
||||
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [cond_in[a:b]], "c_concat": [image_cond_in[a:b]]})
|
||||
else:
|
||||
x_out = torch.zeros_like(x_in)
|
||||
batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
|
||||
for batch_offset in range(0, tensor.shape[0], batch_size):
|
||||
a = batch_offset
|
||||
b = min(a + batch_size, tensor.shape[0])
|
||||
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": torch.cat([tensor[a:b]], uncond) , "c_concat": [image_cond_in[a:b]]})
|
||||
|
||||
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":
|
||||
sd_samplers_common.store_latent(x_out[0:uncond.shape[0]])
|
||||
elif opts.live_preview_content == "Negative prompt":
|
||||
sd_samplers_common.store_latent(x_out[-uncond.shape[0]:])
|
||||
|
||||
denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale, image_cfg_scale)
|
||||
|
||||
if self.mask is not None:
|
||||
denoised = self.init_latent * self.mask + self.nmask * denoised
|
||||
|
||||
self.step += 1
|
||||
|
||||
return denoised
|
||||
|
||||
|
||||
class CFGDenoiser(torch.nn.Module):
|
||||
"""
|
||||
|
|
@ -141,6 +57,7 @@ class CFGDenoiser(torch.nn.Module):
|
|||
self.nmask = None
|
||||
self.init_latent = None
|
||||
self.step = 0
|
||||
self.image_cfg_scale = None
|
||||
|
||||
def combine_denoised(self, x_out, conds_list, uncond, cond_scale):
|
||||
denoised_uncond = x_out[-uncond.shape[0]:]
|
||||
|
|
@ -152,19 +69,36 @@ class CFGDenoiser(torch.nn.Module):
|
|||
|
||||
return denoised
|
||||
|
||||
def combine_denoised_for_edit_model(self, x_out, cond_scale):
|
||||
out_cond, out_img_cond, out_uncond = x_out.chunk(3)
|
||||
denoised = out_uncond + cond_scale * (out_cond - out_img_cond) + self.image_cfg_scale * (out_img_cond - out_uncond)
|
||||
|
||||
return denoised
|
||||
|
||||
def forward(self, x, sigma, uncond, cond, cond_scale, image_cond):
|
||||
if state.interrupted or state.skipped:
|
||||
raise sd_samplers_common.InterruptedException
|
||||
|
||||
# at self.image_cfg_scale == 1.0 produced results for edit model are the same as with normal sampling,
|
||||
# so is_edit_model is set to False to support AND composition.
|
||||
is_edit_model = shared.sd_model.cond_stage_key == "edit" and self.image_cfg_scale is not None and self.image_cfg_scale != 1.0
|
||||
|
||||
conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
|
||||
uncond = prompt_parser.reconstruct_cond_batch(uncond, self.step)
|
||||
|
||||
assert not is_edit_model or all([len(conds) == 1 for conds in conds_list]), "AND is not supported for InstructPix2Pix checkpoint (unless using Image CFG scale = 1.0)"
|
||||
|
||||
batch_size = len(conds_list)
|
||||
repeats = [len(conds_list[i]) for i in range(batch_size)]
|
||||
|
||||
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
|
||||
sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
|
||||
image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
|
||||
if not is_edit_model:
|
||||
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
|
||||
sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
|
||||
image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
|
||||
else:
|
||||
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x] + [x])
|
||||
sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma] + [sigma])
|
||||
image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond] + [torch.zeros_like(self.init_latent)])
|
||||
|
||||
denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)
|
||||
cfg_denoiser_callback(denoiser_params)
|
||||
|
|
@ -173,7 +107,10 @@ class CFGDenoiser(torch.nn.Module):
|
|||
sigma_in = denoiser_params.sigma
|
||||
|
||||
if tensor.shape[1] == uncond.shape[1]:
|
||||
cond_in = torch.cat([tensor, uncond])
|
||||
if not is_edit_model:
|
||||
cond_in = torch.cat([tensor, uncond])
|
||||
else:
|
||||
cond_in = torch.cat([tensor, uncond, uncond])
|
||||
|
||||
if shared.batch_cond_uncond:
|
||||
x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
|
||||
|
|
@ -189,7 +126,13 @@ class CFGDenoiser(torch.nn.Module):
|
|||
for batch_offset in range(0, tensor.shape[0], batch_size):
|
||||
a = batch_offset
|
||||
b = min(a + batch_size, tensor.shape[0])
|
||||
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [tensor[a:b]], "c_concat": [image_cond_in[a:b]]})
|
||||
|
||||
if not is_edit_model:
|
||||
c_crossattn = [tensor[a:b]]
|
||||
else:
|
||||
c_crossattn = torch.cat([tensor[a:b]], uncond)
|
||||
|
||||
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": c_crossattn, "c_concat": [image_cond_in[a:b]]})
|
||||
|
||||
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]:]]})
|
||||
|
||||
|
|
@ -200,7 +143,10 @@ class CFGDenoiser(torch.nn.Module):
|
|||
elif opts.live_preview_content == "Negative prompt":
|
||||
sd_samplers_common.store_latent(x_out[-uncond.shape[0]:])
|
||||
|
||||
denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
|
||||
if not is_edit_model:
|
||||
denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
|
||||
else:
|
||||
denoised = self.combine_denoised_for_edit_model(x_out, cond_scale)
|
||||
|
||||
if self.mask is not None:
|
||||
denoised = self.init_latent * self.mask + self.nmask * denoised
|
||||
|
|
@ -280,12 +226,10 @@ class KDiffusionSampler:
|
|||
return p.steps
|
||||
|
||||
def initialize(self, p):
|
||||
if shared.sd_model.cond_stage_key == "edit" and getattr(p, 'image_cfg_scale', None) != 1:
|
||||
self.model_wrap_cfg = CFGDenoiserEdit(self.model_wrap)
|
||||
|
||||
self.model_wrap_cfg.mask = p.mask if hasattr(p, 'mask') else None
|
||||
self.model_wrap_cfg.nmask = p.nmask if hasattr(p, 'nmask') else None
|
||||
self.model_wrap_cfg.step = 0
|
||||
self.model_wrap_cfg.image_cfg_scale = getattr(p, 'image_cfg_scale', None)
|
||||
self.eta = p.eta if p.eta is not None else opts.eta_ancestral
|
||||
|
||||
k_diffusion.sampling.torch = TorchHijack(self.sampler_noises if self.sampler_noises is not None else [])
|
||||
|
|
@ -355,9 +299,6 @@ class KDiffusionSampler:
|
|||
'cond_scale': p.cfg_scale,
|
||||
}
|
||||
|
||||
if hasattr(p, 'image_cfg_scale') and p.image_cfg_scale != 1 and p.image_cfg_scale != None:
|
||||
extra_args['image_cfg_scale'] = p.image_cfg_scale
|
||||
|
||||
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
|
||||
|
||||
return samples
|
||||
|
|
|
|||
|
|
@ -106,7 +106,7 @@ parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, req
|
|||
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")
|
||||
parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers")
|
||||
|
||||
parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False)
|
||||
|
||||
|
||||
script_loading.preload_extensions(extensions.extensions_dir, parser)
|
||||
|
|
|
|||
|
|
@ -866,8 +866,8 @@ def create_ui():
|
|||
|
||||
with gr.Row():
|
||||
cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="img2img_cfg_scale")
|
||||
image_cfg_scale = gr.Slider(minimum=0, maximum=3.0, step=0.05, label='Image CFG Scale (for pix2pix models)', value=1.5, elem_id="img2img_image_cfg_scale")
|
||||
|
||||
image_cfg_scale = gr.Slider(minimum=0, maximum=3.0, step=0.05, label='Image CFG Scale', value=1.5, elem_id="img2img_image_cfg_scale", visible=shared.sd_model and shared.sd_model.cond_stage_key == "edit")
|
||||
|
||||
with FormRow():
|
||||
denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.75, elem_id="img2img_denoising_strength")
|
||||
|
||||
|
|
@ -1668,6 +1668,12 @@ def create_ui():
|
|||
outputs=[component, text_settings],
|
||||
)
|
||||
|
||||
text_settings.change(
|
||||
fn=lambda: gr.update(visible=shared.sd_model and shared.sd_model.cond_stage_key == "edit"),
|
||||
inputs=[],
|
||||
outputs=[image_cfg_scale],
|
||||
)
|
||||
|
||||
button_set_checkpoint = gr.Button('Change checkpoint', elem_id='change_checkpoint', visible=False)
|
||||
button_set_checkpoint.click(
|
||||
fn=lambda value, _: run_settings_single(value, key='sd_model_checkpoint'),
|
||||
|
|
|
|||
|
|
@ -29,8 +29,9 @@ def add_pages_to_demo(app):
|
|||
if not any([Path(x).resolve() in Path(filename).resolve().parents for x in allowed_dirs]):
|
||||
raise ValueError(f"File cannot be fetched: {filename}. Must be in one of directories registered by extra pages.")
|
||||
|
||||
if os.path.splitext(filename)[1].lower() != ".png":
|
||||
raise ValueError(f"File cannot be fetched: {filename}. Only png.")
|
||||
ext = os.path.splitext(filename)[1].lower()
|
||||
if ext not in (".png", ".jpg"):
|
||||
raise ValueError(f"File cannot be fetched: {filename}. Only png and jpg.")
|
||||
|
||||
# would profit from returning 304
|
||||
return FileResponse(filename, headers={"Accept-Ranges": "bytes"})
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user