lucataco / flux-dev-lora

FLUX.1-Dev LoRA Explorer

  • Public
  • 2M runs
  • GitHub
  • Weights
  • License
Run with an API
Playground API Examples README Versions

FLUX.1-Dev LoRA explorer

Now with img2img support

About

This model is a Cog implementation of exploring Flux.1-Dev LoRAs. This model prioritizes Hugging Face LoRA paths like: “alvdansen/frosting_lane_flux”.

Follow me on Twitter/X @lucataco93

Examples

Under Examples tab, you will find 2 different types of Flux LoRAs

Some are Object LoRAs like this AI character Violeta: lucataco/flux-vlta and this dog named Queso: lucataco/flux-queso

Some are Style LoRAs like this illustration style LoRA alvdansen/frosting_lane_flux and this watercolor style LoRA lucataco/flux-dev-lora

How to run

  • If you want to run a Huggingface LoRA, then use the huggingface model path (ex: alvdansen/frosting_lane_flux) for the value of the hf_lora parameter.

  • If you want to run a Replicate LoRA that you trained, copy the URL from the finished training, and use that for the value of the hf_lora parameter: Replicate-watercolor

  • If you want to use a CivitAI LoRA, use the CivitAI weights URL(ex: https://civitai.com/api/download/models/735262?type=Model&format=SafeTensor) (If the CivitAI LoRA is gated by sign-in access, be sure to add your CivitAI API token at the end of the URL: “&token=<YOUR_API_TOKEN>“)

How to train a LoRA

Check out the Replicate official Flux LoRA trainer

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.