support any input resolution in stable diffusion models #1087
Conversation
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
eaidova
commented
Dec 20, 2024
eaidova
force-pushed
the
ea/sd_any_res
branch
from
ea0f84a to
afbac57
Compare
eaidova
force-pushed
the
ea/sd_any_res
branch
from
afbac57 to
70f073a
Compare
|
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. |
AlexKoff88
approved these changes
Dec 20, 2024
IlyasMoutawwakil
approved these changes
Dec 20, 2024
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Outdated suggestions cannot be applied.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.
What does this PR do?
due to UNet architecture limitations, original stable diffusion pipeline implementation requires that input was always divisible on 64 (CompVis/stable-diffusion#60 (comment)). In diffusers-based pipelines this issue was fixed and model can generate if input resolution nondivisible to 64 too (adjusting sizes between unet blocks), but during tracing we still note that openvino model preserve behaviour with requirement divisibility to 64 (because path with adjusting data resolution is not activated during tracing). This PR fixes this limitation