mirrors/stable-diffusion-webui
1
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2026-01-05 00:31:49 -08:00
Code Issues Projects Releases Packages Wiki Activity

rework hypertile into a built-in extension

Browse source
This commit is contained in:
AUTOMATIC1111 2023-11-26 10:51:45 +03:00
parent 3a9bf4ac10
commit d2e0c1ca13
5 changed files with 183 additions and 151 deletions
Download patch file Download diff file Expand all files Collapse all files

37
modules/processing.py
View file

@ -24,7 +24,6 @@ from modules.shared import opts, cmd_opts, state
import modules.shared as shared
import modules.paths as paths
import modules.face_restoration
from modules.hypertile import set_hypertile_seed, largest_tile_size_available, hypertile_context_unet, hypertile_context_vae
import modules.images as images
import modules.styles
import modules.sd_models as sd_models
@ -861,8 +860,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
p.comment(comment)
p.extra_generation_params.update(model_hijack.extra_generation_params)
set_hypertile_seed(p.seed)
# add batch size + hypertile status to information to reproduce the run
if p.n_iter > 1:
shared.state.job = f"Batch {n+1} out of {p.n_iter}"
@ -874,8 +872,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
else:
if opts.sd_vae_decode_method != 'Full':
p.extra_generation_params['VAE Decoder'] = opts.sd_vae_decode_method
with hypertile_context_vae(p.sd_model.first_stage_model, aspect_ratio=p.width / p.height, tile_size=largest_tile_size_available(p.width, p.height), opts=shared.opts):
x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
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)
@ -1141,25 +1138,23 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):
self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
aspect_ratio = self.width / self.height
x = self.rng.next()
tile_size = largest_tile_size_available(self.width, self.height)
with hypertile_context_vae(self.sd_model.first_stage_model, aspect_ratio=aspect_ratio, tile_size=tile_size, opts=shared.opts):
with hypertile_context_unet(self.sd_model.model, aspect_ratio=aspect_ratio, tile_size=tile_size, is_sdxl=shared.sd_model.is_sdxl, opts=shared.opts):
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
del x
if not self.enable_hr:
return samples
devices.torch_gc()
if self.latent_scale_mode is None:
with hypertile_context_vae(self.sd_model.first_stage_model, aspect_ratio=aspect_ratio, tile_size=tile_size, opts=shared.opts):
decoded_samples = torch.stack(decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)).to(dtype=torch.float32)
decoded_samples = torch.stack(decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)).to(dtype=torch.float32)
else:
decoded_samples = None
with sd_models.SkipWritingToConfig():
sd_models.reload_model_weights(info=self.hr_checkpoint_info)
return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)
def sample_hr_pass(self, samples, decoded_samples, seeds, subseeds, subseed_strength, prompts):
@ -1244,18 +1239,15 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
if self.scripts is not None:
self.scripts.before_hr(self)
tile_size = largest_tile_size_available(target_width, target_height)
aspect_ratio = self.width / self.height
with hypertile_context_vae(self.sd_model.first_stage_model, aspect_ratio=aspect_ratio, tile_size=tile_size, opts=shared.opts):
with hypertile_context_unet(self.sd_model.model, aspect_ratio=aspect_ratio, tile_size=tile_size, is_sdxl=shared.sd_model.is_sdxl, opts=shared.opts):
samples = self.sampler.sample_img2img(self, samples, noise, self.hr_c, self.hr_uc, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
samples = self.sampler.sample_img2img(self, samples, noise, self.hr_c, self.hr_uc, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio())
self.sampler = None
devices.torch_gc()
with hypertile_context_vae(self.sd_model.first_stage_model, aspect_ratio=aspect_ratio, tile_size=tile_size, opts=shared.opts):
decoded_samples = decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)
decoded_samples = decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)
self.is_hr_pass = False
return decoded_samples
@ -1532,11 +1524,8 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
if self.initial_noise_multiplier != 1.0:
self.extra_generation_params["Noise multiplier"] = self.initial_noise_multiplier
x *= self.initial_noise_multiplier
aspect_ratio = self.width / self.height
tile_size = largest_tile_size_available(self.width, self.height)
with hypertile_context_vae(self.sd_model.first_stage_model, aspect_ratio=aspect_ratio, tile_size=tile_size, opts=shared.opts):
with hypertile_context_unet(self.sd_model.model, aspect_ratio=aspect_ratio, tile_size=tile_size, is_sdxl=shared.sd_model.is_sdxl, opts=shared.opts):
samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)
samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)
if self.mask is not None:
samples = samples * self.nmask + self.init_latent * self.mask