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 #14390 from wangqyqq/sdxl-inpaint

Browse Source 
Supporting for SDXL-Inpaint Model
This commit is contained in:
AUTOMATIC1111
2023-12-30 14:49:52 +03:00
committed by GitHub
parent c9c105c7db bfe418a58d
commit 908fb4ea71
4 changed files with 130 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
modules/processing.py
View File

@@ -113,6 +113,21 @@ def txt2img_image_conditioning(sd_model, x, width, height):
return x.new_zeros(x.shape[0], 2*sd_model.noise_augmentor.time_embed.dim, dtype=x.dtype, device=x.device)
else:
sd = sd_model.model.state_dict()
diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
if diffusion_model_input is not None:
if diffusion_model_input.shape[1] == 9:
# The "masked-image" in this case will just be all 0.5 since the entire image is masked.
image_conditioning = torch.ones(x.shape[0], 3, height, width, device=x.device) * 0.5
image_conditioning = images_tensor_to_samples(image_conditioning,
approximation_indexes.get(opts.sd_vae_encode_method))
# 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
# Dummy zero conditioning if we're not using inpainting or unclip models.
# 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.
@@ -371,6 +386,12 @@ class StableDiffusionProcessing:
if self.sampler.conditioning_key == "crossattn-adm":
return self.unclip_image_conditioning(source_image)
sd = self.sampler.model_wrap.inner_model.model.state_dict()
diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
if diffusion_model_input is not None:
if diffusion_model_input.shape[1] == 9:
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)