Merge pull request #3923 from random-thoughtss/master

Fix weighted mask for highres fix
This commit is contained in:
AUTOMATIC1111 2022-11-04 08:59:12 +03:00 committed by GitHub
commit 2cf3d2ac15
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 14 additions and 15 deletions

View File

@ -49,7 +49,7 @@ def expand_crop_region(crop_region, processing_width, processing_height, image_w
ratio_processing = processing_width / processing_height
if ratio_crop_region > ratio_processing:
desired_height = (x2 - x1) * ratio_processing
desired_height = (x2 - x1) / ratio_processing
desired_height_diff = int(desired_height - (y2-y1))
y1 -= desired_height_diff//2
y2 += desired_height_diff - desired_height_diff//2

View File

@ -134,11 +134,7 @@ class StableDiffusionProcessing():
# 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 torch.zeros(
x.shape[0], 5, 1, 1,
dtype=x.dtype,
device=x.device
)
return x.new_zeros(x.shape[0], 5, 1, 1)
height = height or self.height
width = width or self.width
@ -156,11 +152,7 @@ class StableDiffusionProcessing():
def img2img_image_conditioning(self, source_image, latent_image, image_mask = None):
if self.sampler.conditioning_key not in {'hybrid', 'concat'}:
# Dummy zero conditioning if we're not using inpainting model.
return torch.zeros(
latent_image.shape[0], 5, 1, 1,
dtype=latent_image.dtype,
device=latent_image.device
)
return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)
# Handle the different mask inputs
if image_mask is not None:
@ -174,11 +166,11 @@ class StableDiffusionProcessing():
# Inpainting model uses a discretized mask as input, so we round to either 1.0 or 0.0
conditioning_mask = torch.round(conditioning_mask)
else:
conditioning_mask = torch.ones(1, 1, *source_image.shape[-2:])
conditioning_mask = source_image.new_ones(1, 1, *source_image.shape[-2:])
# Create another latent image, this time with a masked version of the original input.
# Smoothly interpolate between the masked and unmasked latent conditioning image using a parameter.
conditioning_mask = conditioning_mask.to(source_image.device)
conditioning_mask = conditioning_mask.to(source_image.device).to(source_image.dtype)
conditioning_image = torch.lerp(
source_image,
source_image * (1.0 - conditioning_mask),
@ -674,6 +666,13 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
if opts.use_scale_latent_for_hires_fix:
samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
# Avoid making the inpainting conditioning unless necessary as
# this does need some extra compute to decode / encode the image again.
if getattr(self, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) < 1.0:
image_conditioning = self.img2img_image_conditioning(decode_first_stage(self.sd_model, samples), samples)
else:
image_conditioning = self.txt2img_image_conditioning(samples)
for i in range(samples.shape[0]):
save_intermediate(samples, i)
@ -700,14 +699,14 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples))
image_conditioning = self.img2img_image_conditioning(decoded_samples, samples)
shared.state.nextjob()
self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, 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)
image_conditioning = self.txt2img_image_conditioning(x)
# GC now before running the next img2img to prevent running out of memory
x = None
devices.torch_gc()