lllyasviel / lllyasviel/ControlNet
Discrepant results
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
Hello, Thanks for your great work.
I tried to reproduce some results in your paper, but got some discrepant results.
For example, I will Human Pose with exactly the same prompt "Michael Jackson's concert". Yet, it seems that the generated pictures are unrelated to the original one. Could you shed some lights on what the reason might be? Thanks!
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 by reviewing the linked paper and comparing the reported Human Pose example with the prompt "Michael Jackson's concert" and the attached generated images. Done would mean identifying enough of the setup to explain the discrepancy or establish a reproducible result; the issue names no source files or tests.
Written by the indexing model from the issue text.
Assessment
- 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