lllyasviel / lllyasviel/ControlNet
High Contrast and Abnormal Colors in Generated Images
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
Hello，I am currently attempting to fine-tune a network for image restoration using ControlNet. However, during the training process, I have noticed that the generated images exhibit extremely high contrast and abnormal colors. I am wondering how I can address this issue. Is it related to the CFG scale?
Thank you very much for your assistance.
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 the ControlNet fine-tuning process described in the report and identify the training configuration and image-generation entry points involved. Reproduce the high-contrast, abnormal-color output if possible, then determine whether CFG scale is relevant and document the conditions and resolution.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100