---
title: matrix-game-modular-2-modular
canonical_url: "https://www.modelscope.cn/models/hf-diffusers/matrix-game-modular-2-modular"
md_url: "https://www.modelscope.cn/models/hf-diffusers/matrix-game-modular-2-modular.md"
repository: hf-diffusers/matrix-game-modular-2-modular
last_updated: 2025-10-09
parameters: 1.6B
tensor_type:
  - BF16
library_name:
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
downloads: 79
stars: 0
---

# matrix-game-modular-2-modular

> matrix-game-modular-2-modular - hf-diffusers 在 ModelScope 开源的模型。Matrix Game 2.0 Modular Pipeline

- **Repository**: hf-diffusers/matrix-game-modular-2-modular
- **Parameters**: 1.6B
- **Downloads**: 79
- **Stars**: 0
- **Last updated**: 2025-10-09

Source: https://www.modelscope.cn/models/hf-diffusers/matrix-game-modular-2-modular

---

# Matrix Game 2.0 Modular Pipeline

## Set Up

```shell
uv venv -p 3.10
uv pip install -r requirements.txt
uv pip install git+https://github.com/huggingface/diffusers.git
```

## How to Use

```python
import torch
from diffusers import ModularPipelineBlocks
from diffusers.utils import export_to_video, load_image
from diffusers.modular_pipelines import WanModularPipeline

class MatrixGameWanModularPipeline(WanModularPipeline):
    """
    A ModularPipeline for MatrixGameWan.

    <Tip warning={true}>

        This is an experimental feature and is likely to change in the future.

    </Tip>
    """

    @property
    def default_sample_height(self):
        return 44

    @property
    def default_sample_width(self):
        return 80

# Download custom blocks for the pipeline
blocks = ModularPipelineBlocks.from_pretrained(
    "diffusers-internal-dev/matrix-game-2-modular",
    trust_remote_code=True,
)

# Initialize the pipeline runtime using the config in the repo
pipe = MatrixGameWanModularPipeline(blocks, "diffusers-internal-dev/matrix-game-2-modular")

# Load the model components of the pipeline
pipe.load_components(
    trust_remote_code=True,
    device_map="cuda",
    torch_dtype={"default": torch.bfloat16, "vae": torch.float32}
)

image = load_image("https://github.com/SkyworkAI/Matrix-Game/blob/main/Matrix-Game-2/demo_images/universal/0016.png?raw=true")
output = pipe(image=image, num_frames=141)
export_to_video(output.values['videos'][0], "matrix-game.mp4")
```

## Providing Actions as Inputs

Each action is represented as a string. The available actions are:

Motion Actions: ["forward", "left", "right"]
Camera Actions: ["camera_l", "camera_r", "camera_u", "camera_d"]
Compound Actions: Combinations of motion and camera actions with an `_` separating actions, e.g. "forward_left", "forward_left_camera_l"

```py
image = load_image("https://github.com/SkyworkAI/Matrix-Game/blob/main/Matrix-Game-2/demo_images/universal/0016.png?raw=true")
output = pipe(image=image, actions=["forward", "camera_l"], num_frames=141)
export_to_video(output.values['videos'][0], "matrix-game.mp4")
```