Hugging Face's logo

WaveCut
/
Cosmos3-Super-Text2Image-Quanto-FP8-Transformer

Text-to-Image
Diffusers
Safetensors
cosmos3
fp8
quanto
optimum-quanto
Model card Files
xet
 Community
WaveCut commited on
Commit
44ed06b
·
verified ·
1 Parent(s): f147518

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ license_link: https://openmdw.ai/license/1-1/
17
 
18
  This repository contains a transformer-only FP8/float8 Quanto quantization for [nvidia/Cosmos3-Super-Text2Image](https://huggingface.co/nvidia/Cosmos3-Super-Text2Image).
19
 
20
- It does not repeat the original model card. Read NVIDIA's card, license, safety notes, and prompt-format guidance here:
21
  [nvidia/Cosmos3-Super-Text2Image](https://huggingface.co/nvidia/Cosmos3-Super-Text2Image).
22
 
23
  Only `transformer/` is provided as a weight artifact. The VAE, scheduler, tokenizers, safety checker, and other components are loaded from the base model.
 
17
 
18
  This repository contains a transformer-only FP8/float8 Quanto quantization for [nvidia/Cosmos3-Super-Text2Image](https://huggingface.co/nvidia/Cosmos3-Super-Text2Image).
19
 
20
+ Read NVIDIA's card, license, safety notes, and prompt-format guidance here:
21
  [nvidia/Cosmos3-Super-Text2Image](https://huggingface.co/nvidia/Cosmos3-Super-Text2Image).
22
 
23
  Only `transformer/` is provided as a weight artifact. The VAE, scheduler, tokenizers, safety checker, and other components are loaded from the base model.