Skip to content

README.md

Latest commit

 

History

History
54 lines (34 loc) · 3.11 KB

README.md

File metadata and controls

54 lines (34 loc) · 3.11 KB
Raw

Next Trainer

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

Qwen-Image-2.1 LoRA training with the DiffSynth engine in Next Trainer

Train Qwen-Image-2.1 LoRA with the DiffSynth engine, with training configuration and TOML preview side by side. Qwen-Image-2.1 beginner's guide (Chinese) · Explore the workspace.

What's new in 3.1.1

  • DiffSynth / Qwen-Image-2.1: single-GPU BF16 text-to-image and Edit LoRA training with an isolated engine environment, target output images plus multiple input references, drag-and-drop upload, and previews during training.
  • Anima Fast: continue to train Anima 2.9B and T-LoRA with a dedicated runtime.
  • Multiple engines, one workspace: manage Kohya, Anima Fast, Musubi, AI Toolkit, and DiffSynth from the same interface.
  • Smoother training workflows: improved task management, configuration imports, and step/epoch handling.

Full changelog · Qwen-Image-2.1 guide (Chinese) · Anima Fast guide

Supported training engines

Kohya · Anima Fast · Musubi · AI Toolkit · DiffSynth-Studio

Kohya is built in. Install the optional engines from Settings → Training engines, then select the appropriate engine on the training page. 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.

Supported models

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

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

Get started

Windows users: download a portable package, extract it, and use the included launcher. An NVIDIA GPU is required; see setup and package selection.

Release status: 3.1.1 source is on main. Portable packages have their own release schedule; check the version and release notes on Releases. Older packages may not include DiffSynth or Qwen-Image-2.1 support.

For the 3.1.1 source version or Linux setup, follow run from source.

Documentation · Report an issue · Credits · Contributors