hoelee/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-08-04 03:10:21 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #7309 from brkirch/fix-embeddings

Browse Source 
Fix embeddings, upscalers, and refactor `--upcast-sampling`
This commit is contained in:
AUTOMATIC1111
2023-01-28 18:44:36 +03:00
committed by GitHub
parent 41e76d1209 f9edd578e9
commit fecb990deb
6 changed files with 26 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
modules/processing.py
View File

@@ -173,8 +173,7 @@ class StableDiffusionProcessing:
midas_in = torch.from_numpy(transformed["midas_in"][None, ...]).to(device=shared.device)
midas_in = repeat(midas_in, "1 ... -> n ...", n=self.batch_size)
conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image.to(devices.dtype_vae) if devices.unet_needs_upcast else source_image))
conditioning_image = conditioning_image.float() if devices.unet_needs_upcast else conditioning_image
conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))
conditioning = torch.nn.functional.interpolate(
self.sd_model.depth_model(midas_in),
size=conditioning_image.shape[2:],
@@ -218,7 +217,7 @@ class StableDiffusionProcessing:
)
# Encode the new masked image using first stage of network.
conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image.to(devices.dtype_vae) if devices.unet_needs_upcast else conditioning_image))
conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image))
# Create the concatenated conditioning tensor to be fed to `c_concat`
conditioning_mask = torch.nn.functional.interpolate(conditioning_mask, size=latent_image.shape[-2:])
@@ -229,16 +228,18 @@ class StableDiffusionProcessing:
return image_conditioning
def img2img_image_conditioning(self, source_image, latent_image, image_mask=None):
source_image = devices.cond_cast_float(source_image)
# HACK: Using introspection as the Depth2Image model doesn't appear to uniquely
# identify itself with a field common to all models. The conditioning_key is also hybrid.
if isinstance(self.sd_model, LatentDepth2ImageDiffusion):
return self.depth2img_image_conditioning(source_image.float() if devices.unet_needs_upcast else source_image)
return self.depth2img_image_conditioning(source_image)
if self.sd_model.cond_stage_key == "edit":
return self.edit_image_conditioning(source_image)
if self.sampler.conditioning_key in {'hybrid', 'concat'}:
return self.inpainting_image_conditioning(source_image.float() if devices.unet_needs_upcast else source_image, latent_image, image_mask=image_mask)
return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
# Dummy zero conditioning if we're not using inpainting or depth model.
return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)
@@ -418,7 +419,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
def decode_first_stage(model, x):
with devices.autocast(disable=x.dtype == devices.dtype_vae):
x = model.decode_first_stage(x.to(devices.dtype_vae) if devices.unet_needs_upcast else x)
x = model.decode_first_stage(x)
return x
@@ -1007,7 +1008,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
image = torch.from_numpy(batch_images)
image = 2. * image - 1.
image = image.to(device=shared.device, dtype=devices.dtype_vae if devices.unet_needs_upcast else None)
image = image.to(shared.device)
self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image))