lllyasviel / lllyasviel/ControlNet

Request: Implement as much as possible from the Mikubill repo

Open
#63 1 comment 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

Great project and it is revolutionary for SD. I've modified and added the project to my own application wrapped in a flask server. It works pretty well but I would like to be able to use models without merging them like the A1111 extension and also the control weight is a much needed option as well. Being able to set the denoising value would be good too.

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 model-loading and merging flow, then trace where control weight and denoising values are handled. Define the scope for using unmerged models and exposing those options, and verify each requested capability against the existing application behavior.

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
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.