Add validation for non-positive num_inference_steps in DDPMScheduler#14155
Open
sridhar-3009 wants to merge 1 commit into
Open
Add validation for non-positive num_inference_steps in DDPMScheduler#14155sridhar-3009 wants to merge 1 commit into
sridhar-3009 wants to merge 1 commit into
Conversation
Calling `scheduler.set_timesteps(0)` or a negative value silently produced a zero-length timestep array that later caused a ZeroDivisionError or division-by-zero NaN inside the step loop. Add an explicit guard matching the pattern already present in DDIMScheduler. Fixes huggingface#13394.
github-actions
Bot
added
fixes-issue
schedulers
size/S
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
DDPMScheduler.set_timesteps(0)(or any negative value) silently produced a zero-length timestep tensor. Downstream, this caused aZeroDivisionErroror produced NaN values in the step loop, with no useful error message pointing to the scheduler.DDIMScheduleralready guards against this with an explicitValueError. This PR adds the same check toDDPMScheduler.Changes
src/diffusers/schedulers/scheduling_ddpm.py— add a two-line guard in theelsebranch ofset_timesteps, before the existingnum_train_timestepsupper-bound check:Closes #13394.