Skip to content

[Euler Discrete] do sigmas edits from the pipeline. #6081

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

Closed
sayakpaul wants to merge 4 commits into from
Closed

[Euler Discrete] do sigmas edits from the pipeline. #6081

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5f4418a
do sigmas edits from the pipeline.
sayakpaul Dec 7, 2023
06d7d5f
fix
sayakpaul Dec 7, 2023
a7d8439
Merge branch 'main' into fix/euler-discrete-sigmas
sayakpaul Dec 7, 2023
fb1b795
Merge branch 'main' into fix/euler-discrete-sigmas
sayakpaul Dec 7, 2023
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: 3 additions & 0 deletions src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1106,6 +1106,9 @@ def __call__(

# 4. Prepare timesteps
timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps)
# Helpful when using `torch.compile()` to get a nice graph.
if hasattr(self.scheduler, "sigmas") and self.scheduler.sigmas.device.type == "cuda":
self.scheduler.sigmas = self.scheduler.sigmas.tolist()

# 5. Prepare latent variables
num_channels_latents = self.unet.config.in_channels
Expand Down