FLUX.1-Dev LoRA explorer

About

This model is a Cog implementation of exploring multiple Flux.1-Dev LoRAs

Examples

Under Examples, you will find that Huggingface, Replicate, and CivitAI LoRAs are supported:

a Violeta (Replicate) LoRA paired with a Huggingface LoRA
a Violeta (Replicate) LoRA paired with a CivitAI LoRA
a Queso (Replicate) LoRA paired with a Huggingface LoRA
a Queso (Replicate) LoRA paired with a CivitAI LoRA

If using a CivitAI LoRA that requires you to be logged into download it, you can append your token to the end of the LoRA URL: “&token=<YOUR_API_TOKEN>“

How to run

Find a set of LoRAs from Huggingface, CivitAI, or train one on Replicate, that you’d like to merge with other LoRAs

Add those paths to the hf_loras parameter (be sure to hit ‘Add value’!)

Write a prompt that will activate both (or more) LoRAs. (Ex: ‘a photo of TOK, sftsrv style’)

Play around with the guidance scale at 2 or 5 to bring out artistic styles more, or enhance skin quality.

Max number of LoRAs this model supports concurrently: 20

How to train a LoRA

Check out our official Flux LoRA trainer model here

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.