hoelee/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-08-04 11:12:35 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

use shared function from processing for creating dummy mask when training inpainting model

Browse Source
This commit is contained in:
AUTOMATIC
2023-01-04 17:58:07 +03:00
parent 184e670126
commit 525cea9245
2 changed files with 29 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
modules/processing.py
View File

@@ -76,6 +76,24 @@ def apply_overlay(image, paste_loc, index, overlays):
return image
def txt2img_image_conditioning(sd_model, x, width, height):
if sd_model.model.conditioning_key not in {'hybrid', 'concat'}:
# 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 x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
# The "masked-image" in this case will just be all zeros since the entire image is masked.
image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
image_conditioning = sd_model.get_first_stage_encoding(sd_model.encode_first_stage(image_conditioning))
# 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
class StableDiffusionProcessing():
"""
The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
@@ -139,26 +157,9 @@ class StableDiffusionProcessing():
self.iteration = 0
def txt2img_image_conditioning(self, x, width=None, height=None):
if self.sampler.conditioning_key not in {'hybrid', 'concat'}:
# 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 x.new_zeros(x.shape[0], 5, 1, 1)
self.is_using_inpainting_conditioning = self.sd_model.model.conditioning_key in {'hybrid', 'concat'}
self.is_using_inpainting_conditioning = True
height = height or self.height
width = width or self.width
# The "masked-image" in this case will just be all zeros since the entire image is masked.
image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning))
# 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
return txt2img_image_conditioning(self.sd_model, x, width or self.width, height or self.height)
def depth2img_image_conditioning(self, source_image):
# Use the AddMiDaS helper to Format our source image to suit the MiDaS model