UNet fusion and fp16 conversion for stable diffusion #14248
Merged
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
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| @@ -39,7 +39,7 @@ | |||
| try: | |||
| if self.shape_infer_helper.infer(dynamic_axis_mapping): | |||
| return self.shape_infer_helper | |||
| except: | |||
| except: # noqa | |||
Check notice
Code scanning / CodeQL
Except block handles 'BaseException'
onnxruntime/python/tools/transformers/models/diffusion/convert_to_fp16.py
Fixed
Show fixed
Hide fixed
wangyems
approved these changes
Jan 20, 2023
rui-ren
pushed a commit
that referenced
this pull request
Feb 3, 2023
Add script to fuse nodes to optimized operators in stable diffusion 1.5 models, and a script to convert fp32 models to fp16 models. Tested with stable diffusion 1.5. Note that the optimized model needs onnxruntime-gpu v1.14 (release candidate will be available soon). Note: We will update the script to work with latest diffusers and stable diffusion v2 and v2.1 models.
rui-ren
pushed a commit
that referenced
this pull request
Feb 3, 2023
Add script to fuse nodes to optimized operators in stable diffusion 1.5 models, and a script to convert fp32 models to fp16 models. Tested with stable diffusion 1.5. Note that the optimized model needs onnxruntime-gpu v1.14 (release candidate will be available soon). Note: We will update the script to work with latest diffusers and stable diffusion v2 and v2.1 models.
rui-ren
pushed a commit
that referenced
this pull request
Feb 3, 2023
Add script to fuse nodes to optimized operators in stable diffusion 1.5 models, and a script to convert fp32 models to fp16 models. Tested with stable diffusion 1.5. Note that the optimized model needs onnxruntime-gpu v1.14 (release candidate will be available soon). Note: We will update the script to work with latest diffusers and stable diffusion v2 and v2.1 models.
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.
Description
Add script to fuse nodes to optimized operators in stable diffusion 1.5 models, and a script to convert fp32 models to fp16 models. Tested with stable diffusion 1.5.
Note that the optimized model needs onnxruntime-gpu nightly package (or build source from main branch) or the coming v1.14 (release candidate will be available soon).
Note: We will update the script to work with latest diffusers and stable diffusion v2 and v2.1 models.
Motivation and Context
huggingface/diffusers#489