kohya-ss / kohya-ss/sd-scripts

[Feature Request] Implement LECO to train LoRA for erasing concepts from diffusion models

Open
#833 3 comments 1 reaction 0 assignees View on GitHub
Dominant language
Python
Stars
7.2k
Forks
1.2k
Avg merge
11m
Merged PRs (30d)
2

Description

See https://github.com/p1atdev/LECO, based off https://github.com/rohitgandikota/erasing/tree/main.

This serves to train "sliders"-like LoRA, and I think it would be great addition to the sd-scripts repo.

Contributor guide

No contributing guide indexed for this repository

Research direction

Read the LECO repository and the referenced erasing implementation to understand the proposed training approach and its integration requirements. Then inspect sd-scripts to identify an appropriate entry point for adding LECO-based LoRA training. Done means the feature is integrated into sd-scripts with a defined training workflow and validation against the referenced 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.