Remove forced float64 from onnx stable diffusion pipelines #11054
Conversation
This file contains 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
init_noise_sigma was being set as float64 before multiplying with latents, which changed latents into float64 too, which caused errors with onnxruntime since the latter wanted float16.
init_noise_sigma was being set as float64 before multiplying with latents, which changed latents into float64 too, which caused errors with onnxruntime since the latter wanted float16.
init_noise_sigma was being set as float64 before multiplying with latents, which changed latents into float64 too, which caused errors with onnxruntime since the latter wanted float16.
…mmit Added comment on purpose of init_noise_sigma. This comment exists in related scripts that use the same line of code, but it was missing here.
|
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. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
These commits change "np.float64(self.scheduler.init_noise_sigma)" into just "self.scheduler.init_noise_sigma" for the onnx stable diffusion pipelines. The forced float64 was affecting the latents' dtypes too, and causing an error with onnxruntime, which wanted float16.
I encountered the error while running test-inferences with Olive's stable diffusion example, and eventually tracked down the source of the float64 typing to these lines of code. Simply removing the forced float64 resolved the error and let image-generation finish successfully.