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
Remove orphaned root sound_tokenizer.ckpt/.json (match Nano)
Browse files- README.md +0 -2
- sound_tokenizer.ckpt +0 -3
- sound_tokenizer.json +0 -42
README.md
CHANGED
|
@@ -21,8 +21,6 @@ countDownloads:
|
|
| 21 |
- model_index.json
|
| 22 |
- tokenizer.json
|
| 23 |
- tokenizer_config.json
|
| 24 |
-
- sound_tokenizer.ckpt
|
| 25 |
-
- sound_tokenizer.json
|
| 26 |
- sound_tokenizer/config.json
|
| 27 |
- sound_tokenizer/diffusion_pytorch_model.safetensors
|
| 28 |
- text_tokenizer/tokenizer.json
|
|
|
|
| 21 |
- model_index.json
|
| 22 |
- tokenizer.json
|
| 23 |
- tokenizer_config.json
|
|
|
|
|
|
|
| 24 |
- sound_tokenizer/config.json
|
| 25 |
- sound_tokenizer/diffusion_pytorch_model.safetensors
|
| 26 |
- text_tokenizer/tokenizer.json
|
sound_tokenizer.ckpt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6daeb68a219f3e86c0918f616d78b9ebf073f3d700df63ff1c02d214c081d72d
|
| 3 |
-
size 1985246007
|
|
|
|
|
|
|
|
|
|
|
|
sound_tokenizer.json
DELETED
|
@@ -1,42 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"model_type": "autoencoder_v2",
|
| 3 |
-
"sampling_rate": 48000,
|
| 4 |
-
"stereo": true,
|
| 5 |
-
"use_wav_as_input": true,
|
| 6 |
-
"normalize_volume": true,
|
| 7 |
-
"hop_size": 1920,
|
| 8 |
-
"input_channels": 1,
|
| 9 |
-
"enc_type": "spec_convnext",
|
| 10 |
-
"enc_dim": 192,
|
| 11 |
-
"enc_intermediate_dim": 768,
|
| 12 |
-
"enc_num_layers": 12,
|
| 13 |
-
"enc_num_blocks": 2,
|
| 14 |
-
"enc_n_fft": 64,
|
| 15 |
-
"enc_hop_length": 16,
|
| 16 |
-
"enc_latent_dim": 128,
|
| 17 |
-
"enc_c_mults": [1, 2, 4],
|
| 18 |
-
"enc_strides": [4, 5, 6],
|
| 19 |
-
"enc_identity_init": false,
|
| 20 |
-
"enc_use_snake": true,
|
| 21 |
-
"dec_type": "oobleck",
|
| 22 |
-
"dec_dim": 320,
|
| 23 |
-
"dec_c_mults": [1, 2, 4, 8, 16],
|
| 24 |
-
"dec_strides": [2, 4, 5, 6, 8],
|
| 25 |
-
"dec_use_snake": true,
|
| 26 |
-
"dec_final_tanh": false,
|
| 27 |
-
"dec_out_channels": 2,
|
| 28 |
-
"dec_anti_aliasing": false,
|
| 29 |
-
"dec_use_nearest_upsample": false,
|
| 30 |
-
"dec_use_tanh_at_final": false,
|
| 31 |
-
"bottleneck_type": "vae",
|
| 32 |
-
"bottleneck": {"type": "vae"},
|
| 33 |
-
"activation": "snakebeta",
|
| 34 |
-
"snake_logscale": true,
|
| 35 |
-
"anti_aliasing": false,
|
| 36 |
-
"use_cuda_kernel": false,
|
| 37 |
-
"causal": false,
|
| 38 |
-
"padding_mode": "zeros",
|
| 39 |
-
"vocoder_input_dim": 64,
|
| 40 |
-
"latent_mean": null,
|
| 41 |
-
"latent_std": null
|
| 42 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|