lllyasviel / lllyasviel/ControlNet
Training ControlNet, exclude text caption
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
Anyone know how to to finetune ControlNet on image-to-image tasks, without considering the text prompt at all during the training process? I.e. for image restoration tasks like super resolution/denoising
I know at inference time, we can reduce the unconditional_guidance_scale, and at training time we could just pass in an empty string as a workaround, but I figured the optimal solution would involve completely excluding CLIP from the finetuning process
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
The issue does not identify a file, test, or training entry point. Start by locating the ControlNet finetuning path and tracing how the text prompt reaches CLIP during image-to-image training. Done means defining and validating a training path that excludes text conditioning for restoration tasks such as super resolution or denoising.
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
- 25/100