lllyasviel / lllyasviel/ControlNet

Binary image as control

Open
#428 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
34.1k
Forks
3k
PR merge metrics
No merged PRs in 30d

Description

Awesome project @lllyasviel!
I have a question. I have a dataset of real ID card images (with some text written on them). How should the model perform if I use the binarized image as a control? I did train a model but did not get satisfactory results. Even though the control image (binarized) had the text part clearly outlined, the sampled image's text was blurry and gibberish. Your input would be appreciated.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the binarized control-image and training setup described in the issue, then inspect the repository's ControlNet training and sampling entry points. No file or test is named, so the expected behavior and a completion criterion would need to be established with the maintainers before implementation.

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
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.