-
Notifications
You must be signed in to change notification settings - Fork 2.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat: DW Openpose Processor #5688
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good just would like to have types on our code, and attribution for code that was copied
Should we default the processor to hands as well? |
works for me. have we had a test on mac? |
@Millu Millun, could you update (or point out to me) the docs that need to reflect the fact that the Openpose Image Processor is now removed entirely and the new way to do Openpose is with the |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Updated docs & tested on macOS
@hipsterusername Good to merge I think. |
Let's hold to merge until 3.6.3 is released as this will introduce a breaking change |
6be73ac
to
64aab4e
Compare
What type of PR is this? (check all applicable)
Have you discussed this change with the InvokeAI team?
Have you updated all relevant documentation?
Description
This PR adds the DW Openpose Image Processor for ControlNet to InvokeAI.
DW Openpose Image Processor
- This node takes in an image and lets you generate an openpose skeleton from it. You are able to generate the body skeleton, hand skeleton and also the facial landmarks selectively.Removed
The old
Openpose Image Processor
has been entirely removed. Any current workflow using this node will break. But the fix is simple. Just replace it with the newDW Openpose Image Processor
and you are good to go.After Merge