| # Release note |
|
|
| - Cosmos 1.0 was released with the [Cosmos paper](https://research.nvidia.com/publication/2025-01_cosmos-world-foundation-model-platform-physical-ai). |
| - 13 models were released in the [Hugging Face](https://huggingface.co/collections/nvidia/cosmos-6751e884dc10e013a0a0d8e6) as shown in the table below. |
| - Inference scripts for the models were released in the [Cosmos repository](https://github.com/NVIDIA/Cosmos). |
|
|
| ## Released Models |
|
|
| | Item | Model name | Description | Try it out | |
| |--|------------|----------|----------| |
| |1| [Cosmos-1.0-Diffusion-7B-Text2World](https://huggingface.co/nvidia/Cosmos-1.0-Diffusion-7B-Text2World) | Text to visual world generation | [Inference](cosmos1/models/diffusion/README.md) | |
| |2| [Cosmos-1.0-Diffusion-14B-Text2World](https://huggingface.co/nvidia/Cosmos-1.0-Diffusion-14B-Text2World) | Text to visual world generation | [Inference](cosmos1/models/diffusion/README.md) | |
| |3| [Cosmos-1.0-Diffusion-7B-Video2World](https://huggingface.co/nvidia/Cosmos-1.0-Diffusion-7B-Video2World) | Video + Text based future visual world generation | [Inference](cosmos1/models/diffusion/README.md) | |
| |4| [Cosmos-1.0-Diffusion-14B-Video2World](https://huggingface.co/nvidia/Cosmos-1.0-Diffusion-14B-Video2World) | Video + Text based future visual world generation | [Inference](cosmos1/models/diffusion/README.md) | |
| |5| [Cosmos-1.0-Autoregressive-4B](https://huggingface.co/nvidia/Cosmos-1.0-Autoregressive-4B) | Future visual world generation | [Inference](cosmos1/models/autoregressive/README.md) | |
| |6| [Cosmos-1.0-Autoregressive-12B](https://huggingface.co/nvidia/Cosmos-1.0-Autoregressive-12B) | Future visual world generation | [Inference](cosmos1/models/autoregressive/README.md) | |
| |7| [Cosmos-1.0-Autoregressive-5B-Video2World](https://huggingface.co/nvidia/Cosmos-1.0-Autoregressive-5B-Video2World) | Video + Text based future visual world generation | [Inference](cosmos1/models/autoregressive/README.md) | |
| |8| [Cosmos-1.0-Autoregressive-13B-Video2World](https://huggingface.co/nvidia/Cosmos-1.0-Autoregressive-13B-Video2World) | Video + Text based future visual world generation | [Inference](cosmos1/models/autoregressive/README.md) | |
| |9| [Cosmos-1.0-Tokenizer-CV8x8x8](https://huggingface.co/nvidia/Cosmos-1.0-Tokenizer-CV8x8x8) | Continuous video tokenizer with 8x8x8 compression ratio | [Inference](cosmos1/models/diffusion/README.md) | |
| |10| [Cosmos-1.0-Tokenizer-DV8x16x16](https://huggingface.co/nvidia/Cosmos-1.0-Tokenizer-DV8x16x16) | Discrete video tokenizer with 16x8x8 compression ratio | [Inference](cosmos1/models/autoregressive/README.md) | |
| |11| [Cosmos-1.0-PromptUpsampler-12B-Text2World](https://huggingface.co/nvidia/Cosmos-1.0-Prompt-Upsampler-12B-Text2World) | Prompt upsampler for Text2World | [Inference](cosmos1/models/diffusion/README.md) | |
| |12| [Cosmos-1.0-Diffusion-7B-Decoder-DV8x16x16ToCV8x8x8](https://huggingface.co/nvidia/Cosmos-1.0-Diffusion-7B-Decoder-DV8x16x16ToCV8x8x8) | Diffusion decoder for enhancing Cosmos 1.0 autoregressive WFMs' outputs | [Inference](cosmos1/models/autoregressive/README.md) | |
| |13| [Cosmos-1.0-Guardrail](https://huggingface.co/nvidia/Cosmos-1.0-Guardrail) | Guardrail contains pre-Guard and post-Guard for safe use | Embedded in model inference scripts | |
|
|
