Skip to content

Convert sigmas to np.array in FlowMatch set_timesteps #10088

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.

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 1 commit into from
Dec 3, 2024

Conversation

hlky
Copy link
Contributor

@hlky hlky commented Dec 2, 2024

What does this PR do?

#10081 (comment)

This PR converts sigmas to np.array in FlowMatch set_timesteps, originally passing sigmas to Flux pipelines was tested with np.ndarray but Pipeline input for sigmas is supposed to be list according to type hints.

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@yiyixuxu @vladmandic

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@yiyixuxu
Copy link
Collaborator

yiyixuxu commented Dec 2, 2024

that's really fast!! :rolling_on_the_floor_laughing:
can we also do this on scheduler.set_timesteps too? (we only have a few that support custom sigmas)

@hlky hlky force-pushed the sigmas-flux-pipeline-not-numpy branch from df23205 to 090b391 Compare December 2, 2024 22:24
@hlky hlky changed the title Apply np.array to provided sigmas in Flux pipelines Convert sigmas to np.array in FlowMatch set_timesteps Dec 2, 2024
@hlky
Copy link
Contributor Author

hlky commented Dec 2, 2024

Thanks! I've changed it to apply in set_timesteps like in non-FlowMatch

sigmas = np.array(sigmas).astype(np.float32)

@yiyixuxu yiyixuxu merged commit 30f2e9b into huggingface:main Dec 3, 2024
15 checks passed
lawrence-cj pushed a commit to lawrence-cj/diffusers that referenced this pull request Dec 4, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants