Modify ControlNet inferer so that it takes in context when the diffus… #8360
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
…ion model has context. This should be the standard behavior. Modified tests accordingly. Signed-off-by: Virginia Fernandez <virginia.fernandez@kcl.ac.uk>
Contributor
|
/build |
Contributor
|
/build |
Can-Zhao
pushed a commit
to Can-Zhao/MONAI
that referenced
this pull request
Mar 10, 2025
Project-MONAI#8360) Fixes Project-MONAI#8344 ### Description The ControlNet inferers (latent and not latent) work in such a way that, when conditioning is used, the ControlNet does not take in the conditioning. It should, in theory, exhibit the same behaviour as the diffusion model. I've changed this behaviour, which has included modifying ControlNetDiffusionInferer and ControlNetLatentDiffusionInferer; the methods call, sample and get_likelihood. I've also modified the tests to take this into account. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] New tests added to cover the changes (modified, rather than new) - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. Signed-off-by: Virginia Fernandez <virginia.fernandez@kcl.ac.uk> Co-authored-by: Virginia Fernandez <virginia.fernandez@kcl.ac.uk> Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com> Co-authored-by: YunLiu <55491388+KumoLiu@users.noreply.github.com> Signed-off-by: Can-Zhao <volcanofly@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Fixes #8344
Description
The ControlNet inferers (latent and not latent) work in such a way that, when conditioning is used, the ControlNet does not take in the conditioning. It should, in theory, exhibit the same behaviour as the diffusion model.
I've changed this behaviour, which has included modifying ControlNetDiffusionInferer and ControlNetLatentDiffusionInferer; the methods call, sample and get_likelihood.
I've also modified the tests to take this into account.
Types of changes
./runtests.sh --quick --unittests --disttests.