Skip to content

Fix bf15/fp16 for pipeline_wan_vace.py #12143

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Aug 13, 2025
Merged

Fix bf15/fp16 for pipeline_wan_vace.py #12143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f8cd5b1
Fix bf15/fp16 for pipeline_wan_vace.py
SlimRG Aug 13, 2025
feb49b2
Update pipeline_wan_vace.py
SlimRG Aug 13, 2025
fb751c5
try removing xfail decorator
a-r-r-o-w Aug 13, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions src/diffusers/pipelines/wan/pipeline_wan_vace.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -525,8 +525,7 @@ def prepare_video_latents(
latents = retrieve_latents(self.vae.encode(video), generator, sample_mode="argmax").unbind(0)
latents = ((latents.float() - latents_mean) * latents_std).to(vae_dtype)
else:
mask = mask.to(dtype=vae_dtype)
mask = torch.where(mask > 0.5, 1.0, 0.0)
mask = torch.where(mask > 0.5, 1.0, 0.0).to(dtype=vae_dtype)
inactive = video * (1 - mask)
reactive = video * mask
inactive = retrieve_latents(self.vae.encode(inactive), generator, sample_mode="argmax")
Expand Down
6 changes: 0 additions & 6 deletions tests/lora/test_lora_layers_wanvace.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@
import unittest

import numpy as np
import pytest
import safetensors.torch
import torch
from PIL import Image
Expand Down Expand Up @@ -160,11 +159,6 @@ def test_simple_inference_with_text_lora_fused(self):
def test_simple_inference_with_text_lora_save_load(self):
pass

@pytest.mark.xfail(
condition=True,
reason="RuntimeError: Input type (float) and bias type (c10::BFloat16) should be the same",
strict=True,
)
def test_layerwise_casting_inference_denoiser(self):
super().test_layerwise_casting_inference_denoiser()

Expand Down