Skip to content

[refactor] Make guiders return their inputs #12213

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 7 commits into from
Aug 23, 2025

Conversation

a-r-r-o-w
Copy link
Member

No description provided.

@a-r-r-o-w a-r-r-o-w requested a review from yiyixuxu August 22, 2025 00:30
@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.

@@ -89,7 +92,7 @@ def forward(self, pred_cond: torch.Tensor, pred_uncond: Optional[torch.Tensor] =
if self.guidance_rescale > 0.0:
pred = rescale_noise_cfg(pred, pred_cond, self.guidance_rescale)

return pred, {}
return pred, guider_inputs
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would just define a GuiderOutput

and do

return GuiderOutput(pred=pred, pred_cond=pred_cond)

and in the denoiser step, we can do this for now since we don't need other variables for SDXL/wan/flux

block_state.noise_pred = components.guider(guider_state)[0]

Copy link
Collaborator

@yiyixuxu yiyixuxu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks @a-r-r-o-w !

@yiyixuxu yiyixuxu merged commit a840c39 into main Aug 23, 2025
17 of 18 checks passed
@yiyixuxu yiyixuxu deleted the modular-diffusers/refactor-guider-outputs branch August 23, 2025 16:49
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