lucataco / flux-schnell-lora

FLUX.1-Schnell LoRA Explorer

  • Public
  • 704.7K runs
  • A100 (80GB)
  • GitHub
  • Weights
  • License

Input

*string
Shift + Return to add a new line

Prompt for generated image

string

Aspect ratio for the generated image

Default: "1:1"

file

Input image for image to image mode. The aspect ratio of your output will match this image

number
(minimum: 0, maximum: 1)

Prompt strength (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image.

Default: 0.8

integer
(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

integer
(minimum: 1, maximum: 12)

Number of inference steps

Default: 4

integer

Random seed. Set for reproducible generation

string
Shift + Return to add a new line

Huggingface path, or URL to the LoRA weights. Ex: alvdansen/frosting_lane_flux

number
(minimum: 0, maximum: 1)

Scale for the LoRA weights

Default: 0.8

Including output_format and 2 more...

Output

output
Generated in

Run time and cost

This model costs approximately $0.0068 to run on Replicate, or 147 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 A100 (80GB) GPU hardware. Predictions typically complete within 5 seconds.

Readme

--------------------------------------------------------

Use the OFFICIAL Flux Schnell LoRA model here

It runs much faster with the go_fast feature enabled!

--------------------------------------------------------

FLUX.1-Schnell LoRA explorer

About

This model is a Cog implementation of exploring Flux.1-Schnell LoRAs. his 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.