Instructions to use infosave/MOSS-Image-Base-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/MOSS-Image-Base-cmf with cortiq:
# one Rust binary, no additional dependencies cargo install cortiq-cli # or a prebuilt binary from github.com/infosave2007/cmf/releases hf download infosave/MOSS-Image-Base-cmf --include "*.cmf" --local-dir . ls *.cmf # some repos ship more than one quantization
cortiq imagine FILE.cmf --prompt "a red fox in a snowy forest" --out fox.ppm
- Notebooks
- Google Colab
- Kaggle
Download NOTICE from infosave/MOSS-Image-Base-cmf: direct link, hf CLI and curl.
- Browser
- Download file 632 Bytes
-
https://huggingface.co/infosave/MOSS-Image-Base-cmf/resolve/main/NOTICE
- Command line
-
hf download hf://infosave/MOSS-Image-Base-cmf/NOTICE
-
curl -L -o NOTICE https://huggingface.co/infosave/MOSS-Image-Base-cmf/resolve/main/NOTICE
632 Bytes
| MOSS-Image-Base CMF release | |
| This repository contains quantized/repackaged CMF derivatives of: | |
| OpenMOSS-Team/MOSS-Image-Base | |
| source revision: 85975793d8b3d432f1b6e27f352abaa4c2a4c0d3 | |
| source URL: https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base | |
| The upstream project is distributed under Apache License 2.0. The upstream | |
| LICENSE is included as LICENSE. Packaging was performed by cortiq v0.8.30. | |
| The artifact contents retain only the MOSS inference path: the Qwen3.5 text | |
| encoder, MOSS transformer, and Flux2 decoder path. The upstream visual tower, | |
| VAE encoder, and encoder-side quant_conv are deliberately not included. | |