SimpleTuner¶
SimpleTuner is a multi-modal diffusion model fine-tuning toolkit focused on simplicity and ease of understanding.
-
Get Started
Install SimpleTuner and train your first model in minutes
-
Web UI
Configure and run training through a sleek web interface
-
REST API
Automate training workflows with the HTTP API
-
Cloud Training
Run training on Replicate or distributed workers
-
Multi-User
Enterprise features: SSO, quotas, RBAC, worker orchestration
-
Model Guides
Step-by-step guides for Flux, SD3, SDXL, video models, and more
Features¶
- Multi-modal training - Image, video, and audio generation models
- Web UI & API - Train via browser or automate with REST
- Worker orchestration - Distribute jobs across GPU machines
- Enterprise-ready - LDAP/OIDC SSO, RBAC, quotas, audit logging
- Cloud integration - Replicate, self-hosted workers
- Memory optimization - DeepSpeed, FSDP2, quantization
Supported Models¶
| Type | Models |
|---|---|
| Image | Flux.½, SD3, SDXL, Chroma, Auraflow, PixArt, Sana, Lumina2, HiDream, and more |
| Video | Wan, LTX Video, Hunyuan Video, Kandinsky 5, LongCat |
| Audio | ACE-Step |
See Model Guides for complete documentation.
Community¶
- Discord - Terminus Research Group
- GitHub Issues - Bug reports & feature requests
License¶
SimpleTuner is open source software.