lllyasviel / lllyasviel/ControlNet

Controlling face on the output image with ControlNet.

Open
#389 5 comments 1 reaction 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

Is it possible to use ControlNet architecture to create a model that works like a model produced by LoRA training?

For example:
In Stable Diffusion, I have 2 inputs: text prompt and an image of someone's face. I want this hypothetical ControlNet model to use the exact someone's face on the output image without having need to use LoRA model or something. Is it possible to create this kind of ControlNet model?

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

The issue asks whether ControlNet can preserve an exact person's face from an image while using a text prompt, without identifying a file, entry point, model, or test. Start by reviewing the repository's ControlNet and Stable Diffusion model documentation and examples; done would require a confirmed implementation path or documented answer, plus evidence that the requested identity control works.

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.