lllyasviel / lllyasviel/ControlNet
how to support different size in the latent space when training
Open
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 the great work. there is a question when i train the control net.
when inference the denoise steps, the ddim sample size is not just the64*64, how to make it
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 file, test, or entry point; begin by locating the training and DDIM inference paths that determine the latent sample dimensions. Confirm how non-64×64 latent sizes are represented and define a reproducible training/inference case before determining what successful support should look like.
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