Cosmos
Diffusers
Safetensors
cosmos3_omni
nvidia
cosmos3
vllm
vllm-omni
sglang
sglang-diffusion
text, image, video, audio, and action generation
omnimodel
Instructions to use nvidia/Cosmos3-Super-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos3-Super-FP8 with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Diffusers
How to use nvidia/Cosmos3-Super-FP8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nvidia/Cosmos3-Super-FP8", 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
Fix PyTorch runtime link in model card
Browse filesThe PyTorch link under Software Integration → Runtime Engine(s) points to https://github.com/nvidia/cosmos3, which returns HTTP 404. Update it to https://github.com/NVIDIA/cosmos.
Validation: the replacement URL returns HTTP 200. The link audit across the Super, Nano, and Edge base and FP8 model cards found no other broken links: 90 other external URLs responded successfully and all 44 relative file and local-anchor references passed. Example API endpoints were excluded; inference examples were not executed.
README.md
CHANGED
|
@@ -158,7 +158,7 @@ Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated sys
|
|
| 158 |
|
| 159 |
**Runtime Engine(s):**
|
| 160 |
|
| 161 |
-
- [PyTorch](https://github.com/
|
| 162 |
- [vLLM-Omni](https://github.com/vllm-project/vllm-omni)
|
| 163 |
- [Hugging Face Diffusers](https://huggingface.co/docs/diffusers/en/index)
|
| 164 |
- [SGLang](https://github.com/sgl-project/sglang)
|
|
|
|
| 158 |
|
| 159 |
**Runtime Engine(s):**
|
| 160 |
|
| 161 |
+
- [PyTorch](https://github.com/NVIDIA/cosmos)
|
| 162 |
- [vLLM-Omni](https://github.com/vllm-project/vllm-omni)
|
| 163 |
- [Hugging Face Diffusers](https://huggingface.co/docs/diffusers/en/index)
|
| 164 |
- [SGLang](https://github.com/sgl-project/sglang)
|