lllyasviel / lllyasviel/ControlNet

Integration Challenge: Encoder Architectures in Control Net Input

Open
#599 0 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

I'm looking to play around with the input for the control net. Basically, I want to hook up some encoder architectures in front of the input into the control net. By that, I mean running the conditions through an encoder before tossing them into the control net as conditions.

My issue is figuring out where to slot in this architecture in the code, especially making sure it gets trained alongside the control net during training.

Thanks a lot in advance for your help — I hope I've explained what I'm aiming for clearly enough.

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

No file, test, or training entry point is named. Start by locating the ControlNet input and training pipeline, then clarify which encoder architecture and joint-training behavior are intended. Done would require defined integration and acceptance criteria, which the issue currently does not provide.

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.