Mirror/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2024-06-07 21:20:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix critical issue - unet apply

Browse Source
This commit is contained in:
aria1th 2023-11-17 09:22:27 +09:00
parent 472c22cc8a
commit c40be2252a
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
modules/processing.py
View File

@ -874,7 +874,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
else: else:
if opts.sd_vae_decode_method != 'Full': if opts.sd_vae_decode_method != 'Full':
p.extra_generation_params['VAE Decoder'] = opts.sd_vae_decode_method p.extra_generation_params['VAE Decoder'] = opts.sd_vae_decode_method
with hypertile_context_unet(p.sd_model.first_stage_model, aspect_ratio=p.width / p.height, tile_size=largest_tile_size_available(p.width, p.height), is_sdxl=shared.sd_model.is_sdxl, opts=shared.opts): with hypertile_context_unet(p.sd_model.model, aspect_ratio=p.width / p.height, tile_size=largest_tile_size_available(p.width, p.height), is_sdxl=shared.sd_model.is_sdxl, 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.stack(x_samples_ddim).float()
@ -1145,7 +1145,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
x = self.rng.next() x = self.rng.next()
tile_size = largest_tile_size_available(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_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.first_stage_model, aspect_ratio=aspect_ratio, tile_size=tile_size, is_sdxl=shared.sd_model.is_sdxl, 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):
devices.torch_gc() devices.torch_gc()
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 del x
@ -1247,7 +1247,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
tile_size = largest_tile_size_available(target_width, target_height) tile_size = largest_tile_size_available(target_width, target_height)
aspect_ratio = self.width / self.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_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.first_stage_model, aspect_ratio=aspect_ratio, tile_size=tile_size, is_sdxl=shared.sd_model.is_sdxl, 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()) sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio())
@ -1535,7 +1535,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
aspect_ratio = self.width / self.height aspect_ratio = self.width / self.height
tile_size = largest_tile_size_available(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_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.first_stage_model, aspect_ratio=aspect_ratio, tile_size=tile_size, is_sdxl=shared.sd_model.is_sdxl, 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):
devices.torch_gc() devices.torch_gc()
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)