lllyasviel / lllyasviel/ControlNet
normal-map-model: unexpected output
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
Awesome work! :)
One Problem, I tried the normals model and don't get any good results when I provide my own normals map.
Here is what I mean:
1. my own normals map and the output (output completely useless)
1. my own normals map, additionally preprocessed with the normals preprocessor, and the output (output as expected)
Why I get completely useless outputs with my own normals map? Is it the wrong color scheme?
Maybe you can share your code on how you convert depth maps to normal maps so that I can replicate the color scheme :)
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 comparing the user-provided normals map with the same map after the normals preprocessor, using the attached input and output examples as the reproduction case. Inspect the normals-model entry point and preprocessing path to determine what input representation is expected. Done means documenting or correcting the accepted normals-map format so the direct input produces the expected output.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100