lllyasviel / lllyasviel/ControlNet
Comtrolnet as a decensoring engine
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
Before I spend money on gpus I want to ask you. Would it be possibile to train SD with controlnet to take a censored nsfw image as an input and automatically inpainting it in the right spot? What I mean is if I train CN and SD with censored <=> uncensored pairs would it learn to decensore an img?
The censorship usually consists in pixelated area or black strips
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 names no files, tests, or entry points. Start by evaluating whether paired censored and uncensored images can train ControlNet for pixelated areas or black strips, and clarify the intended training setup and success criteria. Done would require a documented feasibility result or a reproducible training path.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100