Note: This is a work in progress

About

This model is an implementation of SimpleTuner, specifically modified to train a LoRA on FLUX.1-Dev.

How to run

At this time you need square images, preferably 1024x1024, with captions as file names. Minimum number of images is 12. Upload images as a zip/tar file.

You need a valid Huggingface key with access to the Flux-dev weights to train a LoRA

Once finished, download your zip file and use the safetensors file

Max time to run a training: 35min

Licensing and commercial use

If you generate images on Replicate with FLUX.1 models and their fine-tunes, then you can use the images commercially.

If you download the weights off Replicate and generate images on your own computer, you can’t use the images commercially.