lucataco / flux-dev-multi-lora

FLUX.1-Dev Multi LoRA Explorer

  • Public
  • 475.8K runs
  • GitHub
  • Weights
  • License
Run with an API
Playground API Examples README Versions

Examples

View more

Run time and cost

This model costs approximately $0.033 to run on Replicate, or 30 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia H100 GPU hardware. Predictions typically complete within 22 seconds. The predict time for this model varies significantly based on the inputs.

Readme

FLUX.1-Dev LoRA explorer

About

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

Follow me on Twitter/X @lucataco93

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.