Fix deepcache for svd #438
Merged
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Outdated suggestions cannot be applied.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.
ComfyUI Node and Example
Node name:
Example workflow:
Single test of SVD DeepCache:
Depending on the new oneflow community edition
cuda 11.8:
python3 -m pip install --pre oneflow -f https://oneflow-pro.oss-cn-beijing.aliyuncs.com/branch/community/cu118
cuda12.1:
python3 -m pip install --pre oneflow -f https://oneflow-pro.oss-cn-beijing.aliyuncs.com/branch/community/cu121
cuda12.2:
python3 -m pip install --pre oneflow -f https://oneflow-pro.oss-cn-beijing.aliyuncs.com/branch/community/cu122
SVD UNet iter speed
A100
The above tests are based on the community version of OneFlow.
Result
When using the SVDSpeedup node of onediff, the video quality is lossless. When using the ModuleDeepCacheSpeedup node, there is a slight loss in quality, but the speed increases by more than double.
Thanks to @Dango233 from Stability AI. He inspired us to try our acceleration node(DeepCache with OneDiff compilation) on SVD.