#37 · Primary category: Image Generation
fluxgym
Dead simple FLUX LoRA training UI with LOW VRAM support
Project last updated:07/28/26
GitHub Stars
3.2K
Forks
372
Contributors
7
License
MIT
Why we included this project
Flux Gym is about as close as you get to point-and-click training for FLUX LoRAs on modest hardware. It pairs a Gradio web interface with the Kohya sd-scripts training backend, so instead of working in a terminal you point it at a folder of reference images and click through a short configuration to train a LoRA on a card with 12 to 20GB of VRAM. The Advanced tab exposes the full Kohya feature set once the defaults stop being enough, and you can add other base models by editing a small YAML file. It also downloads the base model automatically on first run and can publish finished LoRAs straight to Hugging Face. For hobbyists and small teams who want custom image LoRAs without living in a terminal, that covers most of the workflow.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.