lllyasviel / lllyasviel/ControlNet
data of reconstruction_gs is wired
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
Hello, I use the data of fill50k, I found that the data of reconstruction_gs is wired
but it should be like this
And my training didn't converge after more than 4k steps, do you guys have any ideas?
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
No source file, test, or entry point is named. Start by inspecting the fill50k data and the reconstruction_gs output shown in the report, then reproduce the training run beyond 4k steps; done means identifying whether the data is malformed and explaining or fixing the non-convergence.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100