Train Flux LoRA

Warning

If you're not a beginner, check out the original repo: https://github.com/ostris/ai-toolkit. This script is just for beginners.

RunpodFlux.mp4

This is meant to be run on the following spec server:

Specification	Recommended Value
GPU	Minimum 24GB VRAM (e.g., A40, A5000, 3090). Use 48GB VRAM for image generation.
Container Size	Minimum 40GB. Set to 60GB if you also want to generate images.
Volume Size	20GB

Setup

1. Initialize

   curl -s https://geocine.github.io/flux/init.sh | sh
   

2. Paste your huggingface token on the token file.

3. Upload your photos on data folder

4. Modify prompts and trigger_word on config.yaml

5. Start training

   ./run.sh
   

6. After training your model, you can download it from the output folder. Checkout the generate images documentation.