# EnerVerse-AC

An action-conditioned robot world model from AgiBot that generates the camera view a robot arm would see while it carries out a given sequence of actions. The released weights were trained only on the open AgiBot World dataset and are licensed for non-commercial use.

Organization: AgiBot. Released: May 2025. Kind: Robotics.

## What you control

- One start frame from the robot's camera
- An action sequence for the robot
- The camera's extrinsic and intrinsic parameters

## License

Weights: Available (https://huggingface.co/agibot-world/EnerVerse-AC). Declared license: CC BY-NC-SA 4.0.
No. The model card declares CC BY-NC-SA 4.0: no commercial use, and anything you build from the weights must use the same license.

## Real-time

No real-time claim.

## How to run it

1. Create a Python 3.10 conda environment and install requirements.txt and PyTorch3D.
2. Download the single-view checkpoint from Hugging Face and the CLIP weights, and set both paths in the configs.
3. Prepare a start frame, an action file and camera parameter files; the repository includes a script that converts AgiBot World episodes into this format.

## Where to try

No hosted destination verified.

## Sources

- [Project source](https://github.com/AgibotTech/EnerVerse-AC)
- [Weights and model card](https://huggingface.co/agibot-world/EnerVerse-AC)

## Questions

### Is EnerVerse-AC open source?

EnerVerse-AC publishes downloadable weights under CC BY-NC-SA 4.0. Read the license terms before you build on it.

### Can I use EnerVerse-AC commercially?

No. The model card declares CC BY-NC-SA 4.0: no commercial use, and anything you build from the weights must use the same license.

### Does EnerVerse-AC run in real time?

The cited sources do not claim real-time operation.

### Where can I try EnerVerse-AC?

No hosted version was verified; run the published weights yourself.

### What does EnerVerse-AC take as input?

You give it one start frame from the robot's camera, an action sequence for the robot and the camera's extrinsic and intrinsic parameters.

### How do I run EnerVerse-AC?

Following the official instructions: Create a Python 3.10 conda environment and install requirements.txt and PyTorch3D. Download the single-view checkpoint from Hugging Face and the CLIP weights, and set both paths in the configs. Prepare a start frame, an action file and camera parameter files; the repository includes a script that converts AgiBot World episodes into this format.

### What are alternatives to EnerVerse-AC?

Similar models in this directory include 1X World Model (open weights, permissive license), Ctrl-World (open weights, permissive license) and LingBot-World 2.0 (open weights, non-commercial).

Checked 2026-11-03. Corrections: https://github.com/windflow-labs/world-model-directory