Forward from: Метаверсище и ИИще
Сегодня, конечно, день Нвидия.
Они опенсорснули код Cosmos, и это, конечно, космос!
Developer-first world foundation model platform designed to help Physical AI developers build their Physical AI systems better and faster
Долго писать, это опенсорсная World Model.
Выглядит очень круто, го тестировать. Там и video search, и 3Д, и метаверсищще.
Pre-trained Diffusion-based world foundation models for Text2World and Video2World generation where a user can generate visual simulation based on text prompts and video prompts.
Pre-trained Autoregressive-based world foundation models for Video2World generation where a user can generate visual simulation based on video prompts and optional text prompts.
Video tokenizers for tokenizing videos into continuous tokens (latent vectors) and discrete tokens (integers) efficiently and effectively.
Post-training scripts to post-train the pre-trained world foundation models for various Physical AI setup.
Video curation pipeline for building your own video dataset.
https://github.com/NVIDIA/Cosmos
Ссылки:
https://www.nvidia.com/en-us/ai/cosmos/
https://huggingface.co/nvidia/Cosmos-1.0-Guardrail
@cgevent
Они опенсорснули код Cosmos, и это, конечно, космос!
Developer-first world foundation model platform designed to help Physical AI developers build their Physical AI systems better and faster
Долго писать, это опенсорсная World Model.
Выглядит очень круто, го тестировать. Там и video search, и 3Д, и метаверсищще.
Pre-trained Diffusion-based world foundation models for Text2World and Video2World generation where a user can generate visual simulation based on text prompts and video prompts.
Pre-trained Autoregressive-based world foundation models for Video2World generation where a user can generate visual simulation based on video prompts and optional text prompts.
Video tokenizers for tokenizing videos into continuous tokens (latent vectors) and discrete tokens (integers) efficiently and effectively.
Post-training scripts to post-train the pre-trained world foundation models for various Physical AI setup.
Video curation pipeline for building your own video dataset.
https://github.com/NVIDIA/Cosmos
Ссылки:
https://www.nvidia.com/en-us/ai/cosmos/
https://huggingface.co/nvidia/Cosmos-1.0-Guardrail
@cgevent