---
base_model: nvidia/Cosmos3-Nano
license: other
license_name: openmdw1.1-license
license_link: https://openmdw.ai/license/1-1/
pipeline_tag: image-to-video
tags:
- world-model
- neural-rendering
- video-generation
- autoregressive
---

# AgentGarten renderer

The real-time neural renderer of [AgentGarten: Code Worlds for Evolving Agents](https://huggingface.co/papers/2610.12374).
A code world (a simulator or a game engine) keeps the state and runs the rules; this model turns the depth and surface
normals it exports into the observations an agent sees, block by block.

- Paper: https://huggingface.co/papers/2610.12374
- Blog: https://mirros.ai/blog/worlds-for-evolving-agents
- Technical report: https://mirros.ai/report/agent-garten.pdf
- Project page: https://mirros-lab.github.io/agent-garten
- Code: https://github.com/MirroS-Lab/AgentGarten

## What is in this repository

| File | Contents |
| --- | --- |
| `student.safetensors` | The few-step autoregressive generation tower (7.0 B parameters, BF16), distilled with Adversarial Forcing |
| `und.safetensors` | The frozen text tower of Cosmos3-Nano, unchanged |
| `text_tokenizer/` | The Cosmos3-Nano text tokenizer, unchanged |
| `config.yaml`, `manifest.json` | Network configuration and the file list the loader reads |

The model starts from [Cosmos3-Nano](https://huggingface.co/nvidia/Cosmos3-Nano). It was adapted to depth and normal
conditions, trained as a block-causal autoregressive model, and distilled into a four-step student. Video is encoded
and decoded with the [Wan 2.2 VAE](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B), which is not included here.

## Use

Install the [AgentGarten code](https://github.com/MirroS-Lab/AgentGarten), then:

```bash
hf download MirroS-Lab/AgentGarten-renderer --local-dir weights/AgentGarten-renderer
hf download Wan-AI/Wan2.2-TI2V-5B Wan2.2_VAE.pth --local-dir weights/Wan2.2-TI2V-5B
```

```python
from wm.inference.cosmos3 import inspect_artifact, load_artifact
from wm.inference.serving import prepare_serving
from wm.networks.cosmos3.streaming import Cosmos3Stream, StreamPolicy

artifact = load_artifact(inspect_artifact("weights/AgentGarten-renderer"))
prepare_serving(artifact.student)
stream = Cosmos3Stream(artifact.student, StreamPolicy())
```

The repository's README shows the streaming loop: each block of four latent frames is denoised in four steps and then
committed to the key-value cache, so the conditions of the next block can depend on what was just generated.

## License

The weights derive from Cosmos3-Nano and are released under the same
[OpenMDW License Agreement, version 1.1](https://openmdw.ai/license/1-1/). The text tower and the tokenizer are
NVIDIA's files, redistributed unchanged under that license.