Skip to content

About

Multi-engine LoRA trainer for game characters and art styles. Train MOSS-Image, Qwen-Image-2.1, Krea 2, Anima and more in one workspace.

Topics

Resources

Stars

287 stars

Watchers

2 watching

Forks

Latest commit

 

History

1,818 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Next Trainer — 支持 MOSS 训练

A local training workbench for multiple models and engines
Prepare datasets, train models, and follow your runs in one place.

Download · Quick start · Documentation · 中文

MOSS-Image training showcase

A 100-step style LoRA test by KohakuBlueleaf, trained with their KohakuMossTrainer. The top row shows the base model; the bottom row shows the LoRA results. Shared with the author's permission as a MOSS-Image training example; these results were produced with KohakuMossTrainer (also available as an optional engine in the current source version).

MOSS-Image base model and 100-step style LoRA comparison by KohakuBlueleaf

What's new in 3.3.0

  • Multi-engine workbench: Kohya, Anima Fast, Musubi, AI Toolkit, DiffSynth-Studio, and MOSS (anima_lora) are presented through one engine workflow, with an updated model/engine matrix and tutorial index.
  • Independent Kohya runtime: Kohya uses its own environment under extensions/kohya/; trainer source updates are separated from engine installation, repair, and auditing.
  • Kohya survives updates: source and portable-package updates preserve user-owned training runtimes; the portable updater excludes Next-Trainer/extensions/ so updating the main program does not uninstall Kohya.
  • MOSS-Image: Kohya remains the recommended/default engine. The current source also integrates optional KohakuMossTrainer and anima_lora paths; availability in portable packages depends on the package version.
  • AI Toolkit and Ideogram 4: AI Toolkit training and an Ideogram 4 LoRA entry are available as optional engines and are not force-installed.
  • Plugin marketplace: the currently empty marketplace is hidden from users and skipped by default, so its unused dependencies are not downloaded.
  • 3.3.1-dev portable package: a sub-2 GB lite package includes the base runtime, frontend, WD tagger model, and offline tokenizer assets without preinstalling Kohya.

Full changelog

Get started

Windows users: download the current Next-Trainer-v3.3.1-dev-lite.7z, extract it, and use the included launcher. It contains the base runtime, frontend, WD tagger model, and offline tokenizer assets. Kohya is not preinstalled, and the empty plugin marketplace is not downloaded; install a training engine from Settings → Training engines when needed. An NVIDIA GPU is required; see setup and package selection.

Release status: the recommended portable package is 3.3.1-dev. The larger preinstalled-Kohya package is distributed separately from GitHub Releases; the empty plugin marketplace is hidden from users and skipped by default during builds.

For the latest source version or Linux setup, follow run from source.

Updating

Source installation:

  1. Close the WebUI and stop active training jobs.
  2. Run git status in the project directory and commit or back up any local changes.
  3. For the stable version, switch to main and run git pull --ff-only. To follow the next development version, run git fetch origin and then switch to dev.
  4. Start again with run_gui.bat on Windows or bash run_gui.sh on Linux. If the launcher reports changed dependencies, rerun install-cn.ps1 / setup_environment.py as instructed; do not delete the project directory's user data.

Source updates change repository code only. The installed Kohya environment lives under extensions/kohya/; do not delete it manually. If the UI reports a broken Kohya environment after an upgrade, use Settings → Training engines → Kohya → Repair/Install so the current version can audit or repair it.

Portable package:

  • Prefer Update-Next-Trainer-Release.bat from the package root. It downloads the latest Release and merges the program files. If GitHub Release downloads are unavailable, use Update-Next-Trainer.bat for a Git update.
  • Close the WebUI before updating. The updater preserves Next-Trainer\extensions\, models, outputs, logs, training data, and configuration. Next-Trainer\extensions\kohya\ is the independent Kohya environment and is excluded from the update merge.
  • Start again with run_gui.bat. If the launcher reports changed dependencies, run the included update\update_dependencies.bat; do not delete python_embeded or extensions\kohya first.

Old portable packages without an updater: do not extract a new 7z directly over the old directory. Close the application, copy the old Next-Trainer\extensions\kohya\ directory to a safe location, extract the new package into a new directory, then restore that directory to Next-Trainer\extensions\kohya\. Also migrate sd-models, output, logs, train, config, huggingface, and tagger-models. Launch from the new package. This keeps the program update separate from the Kohya environment and avoids losing the engine through an old overwrite workflow.

The lite package does not include Kohya. Install it from Settings → Training engines when needed. After installation, use the updater above and keep Next-Trainer\extensions\kohya\; updating the main program will not uninstall Kohya. See the portable update contract for the detailed rules.

Supported training engines

One interface, multiple training engines — concept illustration

Kohya · Anima Fast · Musubi · AI Toolkit · DiffSynth-Studio · KohakuMossTrainer · MOSS (anima_lora)

Install engines from Settings → Training engines, then select the appropriate engine on the training page. After upgrading from 3.1.1 or older, install Kohya once before running Kohya training. Available engines depend on your trainer version; not every model or feature supported upstream is integrated here.

For Qwen-Image-2.1, select DiffSynth-Studio → LoRA, then choose Text-to-image or Edit. Edit currently requires batch size 1 and can use gradient accumulation for a larger effective batch.

For MOSS-Image LoRA, use Kohya (recommended and selected by default); KohakuMossTrainer (high-performance LyCORIS trainer by KohakuBlueleaf) and MOSS (anima_lora) are also available as optional engines.

Supported models

Supported models — concept illustration, not model output samples

MOSS-Image · Qwen-Image-2.1 · Anima · SD 1.5 · SDXL · Flux · FLUX.2 Klein · Krea 2 · Ideogram 4

Training targets, hardware requirements, and optional engine installation vary by model. See the training tutorials below.

Model / engine compatibility

✅ = an integrated LoRA entry; — = no integrated entry. This table follows this branch's training modules, not the full capabilities of upstream engines. Model variants and hardware requirements still depend on the selected engine.

Model Kohya Anima Fast Musubi AI Toolkit DiffSynth-Studio KohakuMossTrainer MOSS (anima_lora)
MOSS-Image ✅ — — — — ✅ ✅
Qwen-Image-2.1 — — — ✅ ✅ — —
Krea 2 — — ✅ ✅ — — —
Anima ✅ ✅ — ✅ — — —
FLUX.2 Klein — — — ✅ — — —
Ideogram 4 — — ✅ ✅ — — —
Flux ✅ — — ✅ — — —
SDXL ✅ — — ✅ — — —
SD 1.5 ✅ — — ✅ — — —

Kohya also provides full fine-tuning entries for Anima, SDXL, and SD 1.5. MOSS-Image defaults to Kohya, with KohakuMossTrainer and MOSS (anima_lora) as optional engines. Lumina has a Kohya LoRA entry accessible via ?model=lumina, but is hidden from the normal model picker.

The illustrations above are conceptual; their artwork is not a benchmark or a sample generated by each labelled model.

Training tutorials

Interface tour · Tagger model setup · Training monitor · All documentation


Documentation · Report an issue · Credits · Contributors

About

Multi-engine LoRA trainer for game characters and art styles. Train MOSS-Image, Qwen-Image-2.1, Krea 2, Anima and more in one workspace.

Topics

Resources

Stars

287 stars

Watchers

2 watching

Forks

Releases

Packages

Used by

Contributors

Languages