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 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos3-Super 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 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", 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
Commit ·
2a57944
1
Parent(s): bc962f1
consolidate sglang serve section
Browse files
README.md
CHANGED
|
@@ -926,7 +926,7 @@ Example output:
|
|
| 926 |
|
| 927 |
### SGLang
|
| 928 |
|
| 929 |
-
SGLang
|
| 930 |
|
| 931 |
```bash
|
| 932 |
git clone --branch main https://github.com/sgl-project/sglang.git
|
|
@@ -987,8 +987,6 @@ curl -sS -L "http://localhost:30000/v1/videos/${job_id}/content" \
|
|
| 987 |
|
| 988 |
Video-to-video, video-with-sound, and action generation are not supported by SGLang yet.
|
| 989 |
|
| 990 |
-
[SGLang Diffusion](https://sgl-project.github.io/diffusion) can serve `nvidia/Cosmos3-Super` through OpenAI-compatible image and video generation endpoints.
|
| 991 |
-
|
| 992 |
For complete serving instructions and request examples, see the [Cosmos3 SGLang cookbook](https://lmsysorg.mintlify.app/cookbook/diffusion/Cosmos/Cosmos3).
|
| 993 |
|
| 994 |
## Limitations
|
|
|
|
| 926 |
|
| 927 |
### SGLang
|
| 928 |
|
| 929 |
+
[SGLang Diffusion](https://sgl-project.github.io/diffusion) can serve `nvidia/Cosmos3-Super` through OpenAI-compatible image and video generation endpoints. Install SGLang from the main branch with diffusion dependencies, then start the server:
|
| 930 |
|
| 931 |
```bash
|
| 932 |
git clone --branch main https://github.com/sgl-project/sglang.git
|
|
|
|
| 987 |
|
| 988 |
Video-to-video, video-with-sound, and action generation are not supported by SGLang yet.
|
| 989 |
|
|
|
|
|
|
|
| 990 |
For complete serving instructions and request examples, see the [Cosmos3 SGLang cookbook](https://lmsysorg.mintlify.app/cookbook/diffusion/Cosmos/Cosmos3).
|
| 991 |
|
| 992 |
## Limitations
|