Not-For-All-Audiences

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.

Downloads last month: 24

Safetensors

Model size

12B params

Tensor type

F8_E4M3

Model tree for John6666/flux-dev8-anime-nsfw-fp8-flux

Base model

Zuntan/FluxDev8AnimeNsfw

Finetuned

(1)

this model