Kohya’s GUI
GUI for training LoRA, DreamBooth and fine-tunes for SD, SDXL and FLUX.
- Stars
- 12.6K
- Forks
- 1.6K
- Open issues
- 538
- Last commit
- 2026-08-01
Live from the GitHub API · updated 2026-10-15
What is Kohya’s GUI?
Kohya’s GUI wraps kohya-ss/sd-scripts in a Gradio interface for training LoRA, LyCORIS, DreamBooth and full fine-tunes, with dataset captioning tools.
Key features
- LoRA, DreamBooth and fine-tune training
- SD1.5, SDXL and FLUX support
- Captioning utilities
- Saved training presets
System requirements
- Platforms
- Windows · Linux
- GPU
- NVIDIA
- VRAM
- 8 GB+ for SD1.5 LoRA; 12–24 GB for SDXL/FLUX
- Python
- 3.10/3.11
How to install Kohya’s GUI
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Windows
- 1Clone and run setup.
git clone --recursive https://github.com/bmaltais/kohya_ss.git cd kohya_ss .\setup.bat - 2Launch the GUI.
.\gui.bat
Linux
- 1Clone, set up and launch.
git clone --recursive https://github.com/bmaltais/kohya_ss.git cd kohya_ss ./setup.sh ./gui.sh
Strengths
- Most popular LoRA trainer
- Many options
Limitations
- Lots of settings to learn
Kohya’s GUI alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| 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 | |
| OneTrainer One-stop trainer for diffusion models with a desktop UI. | 3.2K | AGPL-3.0 | 8 GB+ | |
| 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 | — |
Related models
FAQ
Is Kohya’s GUI free?
Yes — Kohya’s GUI is open-source software released under the Apache-2.0 license. Check the license (and any model weight licenses) before commercial use.
Does Kohya’s GUI run on Windows, Mac and Linux?
Kohya’s GUI supports: Windows, Linux.
What hardware do I need for Kohya’s GUI?
NVIDIA. VRAM: 8 GB+ for SD1.5 LoRA; 12–24 GB for SDXL/FLUX
How do I install Kohya’s GUI?
1. Clone and run setup. 2. Launch the GUI.
What are the best Kohya’s GUI alternatives?
Popular alternatives include OneTrainer, AI Toolkit, Unsloth, Axolotl. See the comparison table on this page.