OneTrainer

A newer trainer with a friendlier interface than Kohya's and a good record of supporting new architectures quickly.

Self-hosted
Active
Allowed adult content
Open source

At a glance

Where it runs: Self-hostedYou run it on your own machine. Nothing leaves it unless you send it.
Adult content: AllowedAdult content is permitted within the published rules.
Trains on your content: NoYour content is not used to train models.
Status: ActiveMaintained and working today.
Account needed: No
Licence: AGPL-3.0
Cost: Free and open source.
What it keeps: Local only.

What it takes to run

Graphics memory: 8 GB VRAM, 16 GB recommended
System memory: 16 GB, 32 GB recommended
Disk: about 30 GB
Runs on: Linux, Windows

Find what fits your machine on the tools page — pick your hardware from the first menu.

Covers the same ground as Kohya's GUI — LoRA, fine-tuning, embeddings — with a desktop interface that explains itself better and sensible presets per model family.

The usual advice is to try this one first and fall back to Kohya's when a guide you are following assumes it.

Worth knowing before you start

Fewer tutorials than Kohya's Most written guides still assume the older tool.

What it does

Presets per model family
LoRA and full fine-tuning
Masked training
Sample images during training

How it relates to other tools

an alternative to Kohya's GUI

Signs of life

Checked automatically. These are the only figures on this page a machine wrote, and they say when they were taken.

Last answered: Yes, 3 hours ago Its website responded when we asked.
Stars on GitHub: 3,206 326 forks.
Last commit: 1 day ago2026-09-14 19:54 UTC
Archived copy: Wayback Machine A snapshot, in case this one stops answering.