# Memorizon

Memorizon trains a world model to remember beyond its context window, so long camera-driven videos stay consistent. You give it one image and steer with keyboard actions or a pose trajectory; it is built on Wan2.2-TI2V-5B and released under Apache-2.0.

Organization: MBZUAI (Institute of Foundation Models). Released: October 2026. Kind: Explorable world.

## What you control

- A starting image
- Keyboard actions
- A camera pose trajectory

## License

Weights: Available (https://huggingface.co/Luffuly/memorizon-1280x704-4step). Declared license: Apache-2.0.
The weights' model card declares Apache-2.0, a permissive license that allows commercial use. Check what the model was built on, because a base model's terms can still apply.

## Real-time

No real-time claim. 1280×704 at 16 fps, generated one second at a time by a 4-step distilled model.

## How to run it

1. Clone TingtingLiao/memorizon, create a Python 3.11 conda environment and run pip install -e .
2. Run python scripts/generate.py with the Luffuly/memorizon-1280x704-4step checkpoint and a starting image.
3. Steer it with keyboard actions, one every 0.25 seconds, or replay a recorded trajectory.
4. In Python, the checkpoint loads with MemorizonPipeline.from_pretrained.

## Where to try

No hosted destination verified.

## Sources

- [Project source](https://github.com/TingtingLiao/memorizon)
- [Weights and model card](https://huggingface.co/Luffuly/memorizon-1280x704-4step)

## Questions

### Is Memorizon open source?

Memorizon publishes downloadable weights under Apache-2.0. The declared license is permissive.

### Can I use Memorizon commercially?

The weights' model card declares Apache-2.0, a permissive license that allows commercial use. Check what the model was built on, because a base model's terms can still apply.

### Does Memorizon run in real time?

1280×704 at 16 fps, generated one second at a time by a 4-step distilled model.

### Where can I try Memorizon?

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

### What does Memorizon take as input?

You give it a starting image, keyboard actions and a camera pose trajectory.

### How do I run Memorizon?

Following the official instructions: Clone TingtingLiao/memorizon, create a Python 3.11 conda environment and run pip install -e . Run python scripts/generate.py with the Luffuly/memorizon-1280x704-4step checkpoint and a starting image. Steer it with keyboard actions, one every 0.25 seconds, or replay a recorded trajectory. In Python, the checkpoint loads with MemorizonPipeline.from_pretrained.

### What are alternatives to Memorizon?

Similar models in this directory include ABot-World (open weights, permissive license), AlayaWorld (open weights, custom terms) and DreamX-World (open weights, permissive license).

Checked 2026-10-23. Corrections: https://github.com/windflow-labs/world-model-directory