Skip to content
This repository was archived by the owner on Feb 7, 2025. It is now read-only.

Conversation

Warvito
Copy link
Collaborator

@Warvito Warvito commented Apr 3, 2023

Implements #296

Warvito added 2 commits April 3, 2023 21:21
Signed-off-by: Walter Hugo Lopez Pinaya <ianonimato@hotmail.com>
Signed-off-by: Walter Hugo Lopez Pinaya <ianonimato@hotmail.com>
@Warvito Warvito linked an issue Apr 3, 2023 that may be closed by this pull request
@Warvito Warvito changed the title Add ControlNet [WIP] Add ControlNet Apr 3, 2023
@Warvito Warvito marked this pull request as draft April 3, 2023 21:13
@Warvito Warvito changed the title [WIP] Add ControlNet Add ControlNet Apr 3, 2023
Warvito added 4 commits April 6, 2023 16:53
Signed-off-by: Walter Hugo Lopez Pinaya <ianonimato@hotmail.com>
Signed-off-by: Walter Hugo Lopez Pinaya <ianonimato@hotmail.com>
Signed-off-by: Walter Hugo Lopez Pinaya <ianonimato@hotmail.com>
Signed-off-by: Walter Hugo Lopez Pinaya <ianonimato@hotmail.com>
@Warvito Warvito marked this pull request as ready for review April 8, 2023 08:39
@Warvito Warvito added the need reviewer This PR need a reviewer label Apr 8, 2023
Copy link
Collaborator

@marksgraham marksgraham left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice Walter, looks good to me!

As I understand it, the ControlNet needs to be initalised with the same weights as the trained diffusion model. Should we provide a helper function for that? If you agree, we could do it in another PR as I know @virginiafdez is already working on a tutorial with this controlnet and don't want to hold up its merging anymore

@virginiafdez
Copy link
Contributor

Hello,

For now, I''m not working on a GitHub branch of the repo, but offline as I need to make sure the model works and such. But yeah, I think maybe it's better to do it like @marksgraham says !

@Warvito
Copy link
Collaborator Author

Warvito commented Apr 22, 2023

Nice Walter, looks good to me!

As I understand it, the ControlNet needs to be initalised with the same weights as the trained diffusion model. Should we provide a helper function for that? If you agree, we could do it in another PR as I know @virginiafdez is already working on a tutorial with this controlnet and don't want to hold up its merging anymore

Thank you for the suggestion, @marksgraham . I agree, I think it will be great to have helpers to initialise the controlnets

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

need reviewer This PR need a reviewer

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add support to ControlNet

3 participants