Instructions to use WaveCut/Cosmos3-Super-Text2Image-ModelOpt-NVFP4-Transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/Cosmos3-Super-Text2Image-ModelOpt-NVFP4-Transformer with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/Cosmos3-Super-Text2Image-ModelOpt-NVFP4-Transformer", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Cosmos3-Super-Text2Image-ModelOpt-NVFP4-Transformer / examples /nvidia_example_caption_modelopt_nvfp4.png

- Xet hash:
- 9f1b5c62c54058bb6c224e01a8743de5972d1cef66477fc0e330a949664840da
- Size of remote file:
- 1.27 MB
- SHA256:
- 031f5f3ab02624afd61ee2e582469104521e671e3e4112131bae6084da06c8f4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.