Instructions to use WaveCut/Cosmos3-Super-Text2Image-SDNQ-Uint4-SVD-Transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/Cosmos3-Super-Text2Image-SDNQ-Uint4-SVD-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-SDNQ-Uint4-SVD-Transformer", torch_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 Settings
- Draw Things
- DiffusionBee
Cosmos3-Super-Text2Image-SDNQ-Uint4-SVD-Transformer / examples /nvidia_example_caption_sdnq_uint4_svd.png

- Xet hash:
- e17977629907b9cf17d8ddb6c3c0c30f315ae78bd2895e40ead952105eec98c7
- Size of remote file:
- 1.26 MB
- SHA256:
- ed588aaca0a388e794594b72ed30f551e27fc37d31000f76e29fd2593c9a8212
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.