huggingface/diffusers

[Flux ControlNet] Add support for de-distilled models with CFG

Open

#9,635 opened on Oct 10, 2024

View on GitHub
 (11 comments) (0 reactions) (0 assignees)Python (22,190 stars) (4,562 forks)batch import
contributions-welcomegood first issue

Description

Flux with Inpaiting and ControlNet currently yields bad result with the base model.

To echo this comment, using de-distilled models could potentially help getting better outputs.

Currently the Flux ControlNet pipelines do not support models like https://huggingface.co/nyanko7/flux-dev-de-distill

Contributor guide

Tech stack
pythonpytorch
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Understanding of Flux ControlNet pipelineKnowledge of CFG and model distillationFamiliarity with diffusers library
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
Investigate the current Flux ControlNet pipelines in the diffusers repository to understand how models are loaded and used. Refer to the linked comment in PR #9571 and the de distilled model by nyanko7. Identify where CFG is applied and why de distilled models are not supported. Then modify the pipeline to support loading de distilled models, ensuring compatibility with CFG by adjusting the noise prediction logic accordingly.
[Flux ControlNet] Add support for de-distilled models with CFG · huggingface/diffusers#9635 | Good First Issue