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

Merge pull request #15148 from continue-revolution/conrevo/fix-soft-inpaint

Browse Source 
Fix Soft Inpaint for AnimateDiff
This commit is contained in:
AUTOMATIC1111 2024-03-06 15:36:01 +03:00 committed by GitHub
commit 8904e00842
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
extensions-builtin/soft-inpainting/scripts/soft_inpainting.py
View File

@ -57,10 +57,14 @@ def latent_blend(settings, a, b, t):
# NOTE: We use inplace operations wherever possible. # NOTE: We use inplace operations wherever possible.
# [4][w][h] to [1][4][w][h] if len(t.shape) == 3:
t2 = t.unsqueeze(0) # [4][w][h] to [1][4][w][h]
# [4][w][h] to [1][1][w][h] - the [4] seem redundant. t2 = t.unsqueeze(0)
t3 = t[0].unsqueeze(0).unsqueeze(0) # [4][w][h] to [1][1][w][h] - the [4] seem redundant.
t3 = t[0].unsqueeze(0).unsqueeze(0)
else:
t2 = t
t3 = t[:, 0][:, None]
one_minus_t2 = 1 - t2 one_minus_t2 = 1 - t2
one_minus_t3 = 1 - t3 one_minus_t3 = 1 - t3
@ -135,7 +139,10 @@ def apply_adaptive_masks(
from PIL import Image, ImageOps, ImageFilter from PIL import Image, ImageOps, ImageFilter
# TODO: Bias the blending according to the latent mask, add adjustable parameter for bias control. # TODO: Bias the blending according to the latent mask, add adjustable parameter for bias control.
latent_mask = nmask[0].float() if len(nmask.shape) == 3:
latent_mask = nmask[0].float()
else:
latent_mask = nmask[:, 0].float()
# convert the original mask into a form we use to scale distances for thresholding # convert the original mask into a form we use to scale distances for thresholding
mask_scalar = 1 - (torch.clamp(latent_mask, min=0, max=1) ** (settings.mask_blend_scale / 2)) mask_scalar = 1 - (torch.clamp(latent_mask, min=0, max=1) ** (settings.mask_blend_scale / 2))
mask_scalar = (0.5 * (1 - settings.composite_mask_influence) mask_scalar = (0.5 * (1 - settings.composite_mask_influence)
@ -157,7 +164,14 @@ def apply_adaptive_masks(
percentile_min=0.25, percentile_max=0.75, min_width=1) percentile_min=0.25, percentile_max=0.75, min_width=1)
# The distance at which opacity of original decreases to 50% # The distance at which opacity of original decreases to 50%
half_weighted_distance = settings.composite_difference_threshold * mask_scalar if len(mask_scalar.shape) == 3:
if mask_scalar.shape[0] > i:
half_weighted_distance = settings.composite_difference_threshold * mask_scalar[i]
else:
half_weighted_distance = settings.composite_difference_threshold * mask_scalar[0]
else:
half_weighted_distance = settings.composite_difference_threshold * mask_scalar
converted_mask = converted_mask / half_weighted_distance converted_mask = converted_mask / half_weighted_distance
converted_mask = 1 / (1 + converted_mask ** settings.composite_difference_contrast) converted_mask = 1 / (1 + converted_mask ** settings.composite_difference_contrast)