lllyasviel / lllyasviel/ControlNet
how to Re-train the openpose ControlNet model ?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
hi guys, i test the controlnet openpose will not accurately produce similar number persons, such as the origial pose has three persons, while the output inference has four persons.
now with the train_controlnet_sdxl.py script.
So i want to re-train the openpose model with multi persons cases. Could the loss only care about the image's pose rather not the original full image pixel info?
Any advice will be appreciate
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with train_controlnet_sdxl.py and the multi-person OpenPose behavior described in the issue. Clarify whether the desired outcome is training guidance or a change to the loss and training process; done requires an agreed procedure and validation using poses with multiple people.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100