lllyasviel / lllyasviel/ControlNet
How many patches are divided from 512*512 image for position embedding?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
Thanks for sharing this code!
I'm confused about the position embedding. How many patches are divided from 512*512 image in controlnet? And How can I use my modified pos embedding in controlnet?
Can anyone give some suggestions?
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 identified. Start by locating the ControlNet position-embedding implementation and the path handling 512×512 inputs, then trace how patch counts are computed. Done means documenting the patch count and the supported way to use a modified position embedding.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100