huggingface / huggingface/diffusers

Merge Loras for FLUX

Open
#12,838 1 comment 0 reactions 0 assignees View on GitHub
stale
Dominant language
Python
Stars
34.5k
Forks
7.3k
Avg merge
3d 3h
Merged PRs (30d)
91

Description

The issue is based on https://huggingface.co/docs/diffusers/main/using-diffusers/merge_loras

Is there a similar procedure for merging loras for FLUX models? The guide seems to be specific for UNet based methods. I'm working on FLUX-dev and I would like to perform a linear merge of my loras.

Contributor guide

Open the contributing guide

Research direction

The issue points to the Diffusers merge_loras guide; start by comparing its UNet-based procedure with the FLUX-dev workflow described in the project documentation. Done means providing a verified procedure for linearly merging LoRAs for FLUX models.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.