OneTrainer
One-stop trainer for diffusion models with a desktop UI.
- Star 数
- 3.2K
- Fork 数
- 337
- 未关闭 Issue
- 171
- 最近提交
- 2026-10-12
数据来自 GitHub API · 更新于 2026-10-15
OneTrainer 是什么？
OneTrainer supports full fine-tuning, LoRA and embeddings for SD, SDXL, SD3, FLUX and more, with masked training, automatic captioning and a sampling preview during training.
主要功能
- Fine-tune, LoRA and embedding training
- Masked training
- Built-in captioning
- Training samples and TensorBoard
系统要求
- 平台
- Windows · Linux
- 显卡
- NVIDIA (AMD on Linux)
- 显存
- 8 GB+
- Python
- 3.10–3.12
如何安装 OneTrainer
根据项目 README 整理。开源项目更新很快，请以 GitHub 页面上的最新说明为准。
Windows / Linux
- 1Clone and install.
git clone https://github.com/Nerogar/OneTrainer.git cd OneTrainer ./install.sh # install.bat on Windows - 2Start the UI.
./start-ui.sh # start-ui.bat on Windows
优势
- Clean UI
- Wide model support
不足
- Smaller community than Kohya
OneTrainer 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| OneTrainer One-stop trainer for diffusion models with a desktop UI. | 3.2K | AGPL-3.0 | 8 GB+ | |
| Kohya’s GUI GUI for training LoRA, DreamBooth and fine-tunes for SD, SDXL and FLUX. | 12.6K | Apache-2.0 | 8 GB+ for SD1.5 LoRA; 12–24 GB for SDXL/FLUX | |
| AI Toolkit Ostris’ training suite for FLUX, video and image model LoRAs. | 12.3K | MIT | 24 GB recommended for FLUX | |
| Unsloth Fine-tune LLMs 2× faster with up to 70% less memory. | 78K | Apache-2.0 | 3 GB+ depending on model size | |
| Axolotl Config-driven LLM fine-tuning for many models and techniques. | 12.6K | Apache-2.0 | — | |
| LLaMA-Factory Unified fine-tuning for 100+ LLMs and VLMs with a no-code web UI. | 75.5K | Apache-2.0 | — |
相关模型
常见问题
OneTrainer 免费吗？
是的——OneTrainer 是开源软件，采用 AGPL-3.0 许可证。商用前请确认软件及模型权重的许可条款。
OneTrainer 支持 Windows、Mac 和 Linux 吗？
OneTrainer 支持：Windows, Linux。
运行 OneTrainer 需要什么配置？
NVIDIA (AMD on Linux). VRAM: 8 GB+
如何安装 OneTrainer？
1. Clone and install. 2. Start the UI.
OneTrainer 有哪些好的替代品？
常见替代品包括 Kohya’s GUI, AI Toolkit, Unsloth, Axolotl，详见本页对比表。