lllyasviel / lllyasviel/ControlNet
The discussion about the "sudden converge"
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I found that u said there is a "sudden converge"
I think that because of the uniform sampling of timestep in training.
If use (large timestep, 1000) in the start, and it decay to the (0, 1000) while training
the sudden converge is coming fast with small batch, such as 4.
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 file, test, or entry point is named; first clarify the reported sudden-convergence behavior and reproduce it using the stated timestep schedule and batch size. Done would require an agreed diagnosis and a specific, testable change, neither of which is defined in the issue.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100