John6666's picture
Upload README.md
c26d3b7 verified
metadata
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.
language:
  - en
library_name: diffusers
pipeline_tag: text-to-image
tags:
  - text-to-image
  - Flux
  - fp8
  - float8_e4m3fn
  - anime
  - 8steps
base_model: Zuntan/FluxDev8AnimeNsfw

Original model is here.

Usage Notes (Important)

  • Add fca_style anime, at the beginning of the prompt
    • Reduce photo prompts such as realistic, photo, camera, selfie, etc.
  • Set sampling steps to 8.

This model created by Zuntan.

Notice

This is an experimental conversion in Spaces using a homebrew script. serverless Inference API does not currently support torch float8_e4m3fn, so it does not work. I have not been able to confirm if the conversion is working properly. Please consider this as a test run only.