|
---
|
|
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
|
|
- schnell
|
|
- fp8
|
|
- float8_e4m3fn
|
|
- anime
|
|
- girls
|
|
datasets:
|
|
- KBlueLeaf/danbooru2023-metadata-database
|
|
- KBlueLeaf/danbooru2023-webp-4Mpixel
|
|
base_model: black-forest-labs/FLUX.1-schnell
|
|
---
|
|
|
|
Original model is [here](https://civitai.com/models/731756/sumeshi-flux1-s?modelVersionId=818294).
|
|
|
|
> Note: This model is a Schnell based model, but it requires CFG scale 3.5 or higher (not guidance scale) and 20 steps or more. Needs to be used with clip_l_sumeshi_f1s_v002. (It's the 234.74 MB file in the menu on the right.)
|
|
|
|
This model created by [FA770](https://civitai.com/user/FA770).
|
|
|
|
|
|
## 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. |
