lllyasviel / lllyasviel/FramePack
Censoring
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
I am wondering if the Hunyuan model imposes any kind of censoring. Have been working with a few models with mixed results. Main goal is getting her do drop her clothes. I do know that some of you will say that i need to get a life, and i admit that i don't have one, but i am probably not the only one using this for said purpose so here goes.
I have this hot chick:
Prompt is:
girl is taking off brassiere, with clear movements, full of charm.
https://github.com/user-attachments/assets/81495a61-5cc3-45e0-aa8a-b82ef77a9e85
As seen on the video she is more "simulating" drop of clothes than actually doing it. Is this a censoring issue or is it simply a limitation when using the Hunyuan model? Someone really should create a forum for this so the poor authors should not be bothered with no lifes like me ;-)
Regards
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 repository files, tests, or entry points to inspect. First determine whether the reported Hunyuan behavior is an intentional censoring mechanism or a model limitation; the issue is done only when that distinction is established and documented.
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
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100