Image-to-Video
Cosmos
Diffusers
Safetensors
cosmos3_omni
nvidia
cosmos3
vllm-omni
sglang
sglang-diffusion
video-generation
Instructions to use nvidia/Cosmos3-Super-Image2Video with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos3-Super-Image2Video 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-Image2Video with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nvidia/Cosmos3-Super-Image2Video", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Add modular pipeline index
Browse filesAdds an additive `modular_model_index.json` sidecar for Cosmos3 modular pipeline loading. The existing `model_index.json` and all checkpoint weights are unchanged.
- modular_model_index.json +61 -0
modular_model_index.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_blocks_class_name": "Cosmos3OmniBlocks",
|
| 3 |
+
"_class_name": "Cosmos3OmniModularPipeline",
|
| 4 |
+
"_diffusers_version": "0.39.0.dev0",
|
| 5 |
+
"text_tokenizer": [
|
| 6 |
+
"transformers",
|
| 7 |
+
"Qwen2TokenizerFast",
|
| 8 |
+
{
|
| 9 |
+
"pretrained_model_name_or_path": "nvidia/Cosmos3-Super-Image2Video",
|
| 10 |
+
"revision": null,
|
| 11 |
+
"subfolder": "text_tokenizer",
|
| 12 |
+
"type_hint": [
|
| 13 |
+
"transformers",
|
| 14 |
+
"Qwen2TokenizerFast"
|
| 15 |
+
],
|
| 16 |
+
"variant": null
|
| 17 |
+
}
|
| 18 |
+
],
|
| 19 |
+
"vae": [
|
| 20 |
+
"diffusers",
|
| 21 |
+
"AutoencoderKLWan",
|
| 22 |
+
{
|
| 23 |
+
"pretrained_model_name_or_path": "nvidia/Cosmos3-Super-Image2Video",
|
| 24 |
+
"revision": null,
|
| 25 |
+
"subfolder": "vae",
|
| 26 |
+
"type_hint": [
|
| 27 |
+
"diffusers",
|
| 28 |
+
"AutoencoderKLWan"
|
| 29 |
+
],
|
| 30 |
+
"variant": null
|
| 31 |
+
}
|
| 32 |
+
],
|
| 33 |
+
"transformer": [
|
| 34 |
+
"diffusers",
|
| 35 |
+
"Cosmos3OmniTransformer",
|
| 36 |
+
{
|
| 37 |
+
"pretrained_model_name_or_path": "nvidia/Cosmos3-Super-Image2Video",
|
| 38 |
+
"revision": null,
|
| 39 |
+
"subfolder": "transformer",
|
| 40 |
+
"type_hint": [
|
| 41 |
+
"diffusers",
|
| 42 |
+
"Cosmos3OmniTransformer"
|
| 43 |
+
],
|
| 44 |
+
"variant": null
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"scheduler": [
|
| 48 |
+
"diffusers",
|
| 49 |
+
"UniPCMultistepScheduler",
|
| 50 |
+
{
|
| 51 |
+
"pretrained_model_name_or_path": "nvidia/Cosmos3-Super-Image2Video",
|
| 52 |
+
"revision": null,
|
| 53 |
+
"subfolder": "scheduler",
|
| 54 |
+
"type_hint": [
|
| 55 |
+
"diffusers",
|
| 56 |
+
"UniPCMultistepScheduler"
|
| 57 |
+
],
|
| 58 |
+
"variant": null
|
| 59 |
+
}
|
| 60 |
+
]
|
| 61 |
+
}
|