hoelee/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-08-04 19:22:32 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'AUTOMATIC1111:master' into fix-sd-arch-switch-in-override-settings

Browse Source
This commit is contained in:
Philpax
2023-01-05 05:00:58 +01:00
committed by GitHub
parent fa931733f6 5f4fa942b8
commit 83ca8dd0c9
48 changed files with 1991 additions and 788 deletions
Download Patch File Download Diff File Expand all files Collapse all files

182
modules/processing.py
View File

@@ -76,6 +76,24 @@ def apply_overlay(image, paste_loc, index, overlays):
return image
def txt2img_image_conditioning(sd_model, x, width, height):
if sd_model.model.conditioning_key not in {'hybrid', 'concat'}:
# Dummy zero conditioning if we're not using inpainting model.
# Still takes up a bit of memory, but no encoder call.
# Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
# The "masked-image" in this case will just be all zeros since the entire image is masked.
image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
image_conditioning = sd_model.get_first_stage_encoding(sd_model.encode_first_stage(image_conditioning))
# Add the fake full 1s mask to the first dimension.
image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
image_conditioning = image_conditioning.to(x.dtype)
return image_conditioning
class StableDiffusionProcessing():
"""
The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
@@ -136,28 +154,12 @@ class StableDiffusionProcessing():
self.all_negative_prompts = None
self.all_seeds = None
self.all_subseeds = None
self.iteration = 0
def txt2img_image_conditioning(self, x, width=None, height=None):
if self.sampler.conditioning_key not in {'hybrid', 'concat'}:
# Dummy zero conditioning if we're not using inpainting model.
# Still takes up a bit of memory, but no encoder call.
# Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
return x.new_zeros(x.shape[0], 5, 1, 1)
self.is_using_inpainting_conditioning = self.sd_model.model.conditioning_key in {'hybrid', 'concat'}
self.is_using_inpainting_conditioning = True
height = height or self.height
width = width or self.width
# The "masked-image" in this case will just be all zeros since the entire image is masked.
image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning))
# Add the fake full 1s mask to the first dimension.
image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
image_conditioning = image_conditioning.to(x.dtype)
return image_conditioning
return txt2img_image_conditioning(self.sd_model, x, width or self.width, height or self.height)
def depth2img_image_conditioning(self, source_image):
# Use the AddMiDaS helper to Format our source image to suit the MiDaS model
@@ -239,7 +241,7 @@ class StableDiffusionProcessing():
class Processed:
def __init__(self, p: StableDiffusionProcessing, images_list, seed=-1, info="", subseed=None, all_prompts=None, all_negative_prompts=None, all_seeds=None, all_subseeds=None, index_of_first_image=0, infotexts=None):
def __init__(self, p: StableDiffusionProcessing, images_list, seed=-1, info="", subseed=None, all_prompts=None, all_negative_prompts=None, all_seeds=None, all_subseeds=None, index_of_first_image=0, infotexts=None, comments=""):
self.images = images_list
self.prompt = p.prompt
self.negative_prompt = p.negative_prompt
@@ -247,6 +249,7 @@ class Processed:
self.subseed = subseed
self.subseed_strength = p.subseed_strength
self.info = info
self.comments = comments
self.width = p.width
self.height = p.height
self.sampler_name = p.sampler_name
@@ -338,13 +341,14 @@ def slerp(val, low, high):
def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, seed_resize_from_h=0, seed_resize_from_w=0, p=None):
eta_noise_seed_delta = opts.eta_noise_seed_delta or 0
xs = []
# if we have multiple seeds, this means we are working with batch size>1; this then
# enables the generation of additional tensors with noise that the sampler will use during its processing.
# Using those pre-generated tensors instead of simple torch.randn allows a batch with seeds [100, 101] to
# produce the same images as with two batches [100], [101].
if p is not None and p.sampler is not None and (len(seeds) > 1 and opts.enable_batch_seeds or opts.eta_noise_seed_delta > 0):
if p is not None and p.sampler is not None and (len(seeds) > 1 and opts.enable_batch_seeds or eta_noise_seed_delta > 0):
sampler_noises = [[] for _ in range(p.sampler.number_of_needed_noises(p))]
else:
sampler_noises = None
@@ -384,8 +388,8 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
if sampler_noises is not None:
cnt = p.sampler.number_of_needed_noises(p)
if opts.eta_noise_seed_delta > 0:
torch.manual_seed(seed + opts.eta_noise_seed_delta)
if eta_noise_seed_delta > 0:
torch.manual_seed(seed + eta_noise_seed_delta)
for j in range(cnt):
sampler_noises[j].append(devices.randn_without_seed(tuple(noise_shape)))
@@ -418,7 +422,7 @@ def fix_seed(p):
p.subseed = get_fixed_seed(p.subseed)
def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration=0, position_in_batch=0):
def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iteration=0, position_in_batch=0):
index = position_in_batch + iteration * p.batch_size
clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers)
@@ -544,6 +548,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
state.job_count = p.n_iter
for n in range(p.n_iter):
p.iteration = n
if state.skipped:
state.skipped = False
@@ -647,7 +653,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
devices.torch_gc()
res = Processed(p, output_images, p.all_seeds[0], infotext() + "".join(["\n\n" + x for x in comments]), subseed=p.all_subseeds[0], index_of_first_image=index_of_first_image, infotexts=infotexts)
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)
if p.scripts is not None:
p.scripts.postprocess(p, res)
@@ -658,76 +664,114 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
sampler = None
def __init__(self, enable_hr: bool=False, denoising_strength: float=0.75, firstphase_width: int=0, firstphase_height: int=0, **kwargs):
def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, **kwargs):
super().__init__(**kwargs)
self.enable_hr = enable_hr
self.denoising_strength = denoising_strength
self.firstphase_width = firstphase_width
self.firstphase_height = firstphase_height
self.hr_scale = hr_scale
self.hr_upscaler = hr_upscaler
self.hr_second_pass_steps = hr_second_pass_steps
self.hr_resize_x = hr_resize_x
self.hr_resize_y = hr_resize_y
self.hr_upscale_to_x = hr_resize_x
self.hr_upscale_to_y = hr_resize_y
if firstphase_width != 0 or firstphase_height != 0:
print("firstphase_width/firstphase_height no longer supported; use hr_scale", file=sys.stderr)
self.hr_scale = self.width / firstphase_width
self.width = firstphase_width
self.height = firstphase_height
self.truncate_x = 0
self.truncate_y = 0
def init(self, all_prompts, all_seeds, all_subseeds):
if self.enable_hr:
if state.job_count == -1:
state.job_count = self.n_iter * 2
if self.hr_resize_x == 0 and self.hr_resize_y == 0:
self.extra_generation_params["Hires upscale"] = self.hr_scale
self.hr_upscale_to_x = int(self.width * self.hr_scale)
self.hr_upscale_to_y = int(self.height * self.hr_scale)
else:
state.job_count = state.job_count * 2
self.extra_generation_params["Hires resize"] = f"{self.hr_resize_x}x{self.hr_resize_y}"
self.extra_generation_params["First pass size"] = f"{self.firstphase_width}x{self.firstphase_height}"
if self.firstphase_width == 0 or self.firstphase_height == 0:
desired_pixel_count = 512 * 512
actual_pixel_count = self.width * self.height
scale = math.sqrt(desired_pixel_count / actual_pixel_count)
self.firstphase_width = math.ceil(scale * self.width / 64) * 64
self.firstphase_height = math.ceil(scale * self.height / 64) * 64
firstphase_width_truncated = int(scale * self.width)
firstphase_height_truncated = int(scale * self.height)
else:
width_ratio = self.width / self.firstphase_width
height_ratio = self.height / self.firstphase_height
if width_ratio > height_ratio:
firstphase_width_truncated = self.firstphase_width
firstphase_height_truncated = self.firstphase_width * self.height / self.width
if self.hr_resize_y == 0:
self.hr_upscale_to_x = self.hr_resize_x
self.hr_upscale_to_y = self.hr_resize_x * self.height // self.width
elif self.hr_resize_x == 0:
self.hr_upscale_to_x = self.hr_resize_y * self.width // self.height
self.hr_upscale_to_y = self.hr_resize_y
else:
firstphase_width_truncated = self.firstphase_height * self.width / self.height
firstphase_height_truncated = self.firstphase_height
target_w = self.hr_resize_x
target_h = self.hr_resize_y
src_ratio = self.width / self.height
dst_ratio = self.hr_resize_x / self.hr_resize_y
self.truncate_x = int(self.firstphase_width - firstphase_width_truncated) // opt_f
self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f
if src_ratio < dst_ratio:
self.hr_upscale_to_x = self.hr_resize_x
self.hr_upscale_to_y = self.hr_resize_x * self.height // self.width
else:
self.hr_upscale_to_x = self.hr_resize_y * self.width // self.height
self.hr_upscale_to_y = self.hr_resize_y
self.truncate_x = (self.hr_upscale_to_x - target_w) // opt_f
self.truncate_y = (self.hr_upscale_to_y - target_h) // opt_f
# special case: the user has chosen to do nothing
if self.hr_upscale_to_x == self.width and self.hr_upscale_to_y == self.height:
self.enable_hr = False
self.denoising_strength = None
self.extra_generation_params.pop("Hires upscale", None)
self.extra_generation_params.pop("Hires resize", None)
return
if not state.processing_has_refined_job_count:
if state.job_count == -1:
state.job_count = self.n_iter
shared.total_tqdm.updateTotal((self.steps + (self.hr_second_pass_steps or self.steps)) * state.job_count)
state.job_count = state.job_count * 2
state.processing_has_refined_job_count = True
if self.hr_second_pass_steps:
self.extra_generation_params["Hires steps"] = self.hr_second_pass_steps
if self.hr_upscaler is not None:
self.extra_generation_params["Hires upscaler"] = self.hr_upscaler
def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):
self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_modes.get(shared.latent_upscale_default_mode, "nearest")
if self.enable_hr and latent_scale_mode is None:
assert len([x for x in shared.sd_upscalers if x.name == self.hr_upscaler]) > 0, f"could not find upscaler named {self.hr_upscaler}"
x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
if not self.enable_hr:
x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
return samples
x = create_random_tensors([opt_C, self.firstphase_height // opt_f, self.firstphase_width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x, self.firstphase_width, self.firstphase_height))
target_width = self.hr_upscale_to_x
target_height = self.hr_upscale_to_y
samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2]
"""saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
def save_intermediate(image, index):
"""saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix:
return
if not isinstance(image, Image.Image):
image = sd_samplers.sample_to_image(image, index)
image = sd_samplers.sample_to_image(image, index, approximation=0)
images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")
info = create_infotext(self, self.all_prompts, self.all_seeds, self.all_subseeds, [], iteration=self.iteration, position_in_batch=index)
images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, info=info, suffix="-before-highres-fix")
if opts.use_scale_latent_for_hires_fix:
if latent_scale_mode is not None:
for i in range(samples.shape[0]):
save_intermediate(samples, i)
samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
samples = torch.nn.functional.interpolate(samples, size=(target_height // opt_f, target_width // opt_f), mode=latent_scale_mode["mode"], antialias=latent_scale_mode["antialias"])
# Avoid making the inpainting conditioning unless necessary as
# this does need some extra compute to decode / encode the image again.
@@ -747,7 +791,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
save_intermediate(image, i)
image = images.resize_image(0, image, self.width, self.height)
image = images.resize_image(0, image, target_width, target_height, upscaler_name=self.hr_upscaler)
image = np.array(image).astype(np.float32) / 255.0
image = np.moveaxis(image, 2, 0)
batch_images.append(image)
@@ -764,13 +808,15 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
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]
noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, p=self)
# GC now before running the next img2img to prevent running out of memory
x = None
devices.torch_gc()
samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps, image_conditioning=image_conditioning)
samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
return samples