Skip to content

[tests] fix SVD tests #14687

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
sayakpaul merged 2 commits into from
Sep 2, 2026
Merged

[tests] fix SVD tests #14687

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8b7eb68
fix SVD tests
sayakpaul Sep 2, 2026
67911bf
make comment less confusing
sayakpaul Sep 2, 2026
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
4 changes: 3 additions & 1 deletion src/diffusers/pipelines/stable_video_diffusion/pipeline_stable_video_diffusion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,7 +243,9 @@ def _encode_vae_image(
num_videos_per_prompt: int,
do_classifier_free_guidance: bool,
):
image = image.to(device=device)
# The image comes out of `video_processor.preprocess()` in float32. When `needs_upcasting=False`, the VAE may not
# be in FP32 (for example, it could be in BF16) so we need to cast in this case.
image = image.to(device=device, dtype=self.vae.dtype)
image_latents = self.vae.encode(image).latent_dist.mode()

# duplicate image_latents for each generation per prompt, using mps friendly method
Expand Down
Loading