Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
| Date | Stars |
|---|---|
| 2026-07-31 | 465 |
| 2026-08-04 | 465 |
| 2026-08-06 | 465 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
> [!IMPORTANT]
> ## 🚀 [Cosmos 3 Has Arrived](https://github.com/NVIDIA/Cosmos)
>
> Cosmos 3 is NVIDIA's next-generation foundation model platform for Physical AI. Compared with Cosmos-Predict1, Cosmos 3 delivers significantly stronger world prediction capabilities, producing more accurate, coherent, and physically grounded future-state predictions across a wide range of environments and embodiments.
>
> Beyond improving prediction quality, Cosmos 3 unifies capabilities that previously required multiple specialized models. A single Cosmos 3 model can reason, predict future world states, transfer across domains and modalities, and generate actions and policies for embodied agents within one unified architecture.
>
> This repository is no longer under active development and will receive only limited maintenance updates. Future model releases, features, documentation, and community support will be focused on Cosmos 3.
>
> 👉 Visit the new Cosmos home: https://github.com/NVIDIA/Cosmos
>
> There you will find the latest Cosmos 3 models, technical reports, tutorials, benchmarks, and ecosystem updates.
>
> Thank you for your support of Cosmos-Predict1. We encourage all users to migrate to Cosmos 3 for the latest state-of-the-art Physical AI capabilities.
### [Product Website](https://www.nvidia.com/en-us/ai/cosmos/) | [Hugging Face](https://huggingface.co/collections/nvidia/cosmos-predict1-67c9d1b97678dbf7669c89a7) | [Paper](https://arxiv.org/abs/2501.03575) | [Paper Website](https://research.nvidia.com/labs/dir/cosmos-predict1)
Cosmos-Predict1 is a key branch of Cosmos World Foundation Models (WFMs) specialized for future state prediction, often referred to as world models. The tree main branches of Cosmos WFMs are [cosmos-predict](https://github.com/nvidia-cosmos/cosmos-predict1), [cosmos-transfer](https://github.com/nvidia-cosmos/cosmos-transfer1), and [cosmos-reason](https://github.com/nvidia-cosmos/cosmos-reason1). We visualize the architecture of Cosmos-Predict1 in the following figure.
<p align="center">
<img src="assets/predict1_diagram.png" alt="Cosmos-Predict1 Architecture Diagram">
</p>
Cosmos-Predict1 includes the following:
- **Diffusion-based world foundation models** for Text2World and Video2World generation, where a user can generate visual simulation based on text prompts and video prompts.
- **Autoregressive-based world foundation models** for Video2World generation, where a user can generate visual simulation based on video prompts and optional text prompts.
- **Image and video tokenizers** for tokenizing videos into continuous tokens (latent vectors) and discrete tokens (integers) efficiently and effectively.
- **Post-training scripts** for helping Physical AI builders post-train pre-trained Cosmos-Predict1 for their applications.
## News
- **[2025/05]** **Cosmos AV Single2MultiView** is available! Now you can create dynamic, multi-view clips from just one video. Try it out and tell us what you think!
- [Inference guide](examples/inference_diffusion_single2multiview.md)
- [PyTorch post-training](examples/post-training_diffusion_single2multiview.md)
- [Hugging Face model](https://huggingface.co/nvidia/Cosmos-Predict1-7B-Video2World-Sample-AV-Single2MultiView)
## Example Model Behavior
[Cosmos-Predict Text2World](https://github.com/nvidia-cosmos/cosmos-predict1)
<video src="https://github.com/user-attachments/assets/8abcc5d0-0840-47ae-8f95-10fc0dae7092"> Your browser does not support the video tag.</video>
[Cosmos-Predict Video2World](https://github.com/nvidia-cosmos/cosmos-predict1)
<video src="https://github.com/user-attachments/assets/d598af27-55de-4bc9-b68e-24b70876be9f"> Your browser does not support the video tag. </video>
## Getting Started
We provide a comphrehensive set of examples to illustrate how to perform inference, post-training, etc, with Cosmos-Predict1. Click a relevant example below and start your Cosmos journey.
### Installation
Please refer to [INSTALL.mdExcerpt of 10,436 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d7aa0c422a9b7161, llm:Description: "Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications."
matched fp:d7aa0c422a9b7161, llm:Description: "Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications."