kohya-ss / kohya-ss/sd-scripts

how to build dataset.toml for training controlnet with flux-dev?

Open
#2,024 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7.2k
Forks
1.2k
Avg merge
11m
Merged PRs (30d)
2

Description

Thanks your sharing, I want to train a controlnet with flux.1-dev model, and I can see your readme support it. I want to try, but I don`t know how to build a dataset.toml file , Is there a example ? My dataset struct is "condition_image_dir", "captions", "target_image_dir", three import parameters

Contributor guide

No contributing guide indexed for this repository

Research direction

Read the README's Flux.1-dev training instructions and the references to dataset.toml. Check how condition_image_dir, captions, and target_image_dir are expected to map into the dataset configuration. Done means the documentation includes a usable example for this dataset structure.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.