---
title: Metric-Video-Depth-Anything-Large-MLX
canonical_url: "https://www.modelscope.cn/models/mlx-community/Metric-Video-Depth-Anything-Large-MLX"
md_url: "https://www.modelscope.cn/models/mlx-community/Metric-Video-Depth-Anything-Large-MLX.md"
repository: mlx-community/Metric-Video-Depth-Anything-Large-MLX
last_updated: 2026-09-01
license: cc-by-nc-4.0
model_type:
  - video_depth_anything
parameters: 384.6M
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 4
stars: 0
tags:
  - mlx
  - depth-estimation
  - video-depth-anything
---

# Metric-Video-Depth-Anything-Large-MLX

> Metric-Video-Depth-Anything-Large-MLX - mlx-community 在 ModelScope 开源的模型。Metric Video Depth Anything Large (MLX)

mlx-community/Metric-Video-Depth-Anything-Large-MLX 是 ModelScope 魔搭社区上的 384.6M 参数机器学习模型，采用 cc-by-nc-4.0 许可。

- **Repository**: mlx-community/Metric-Video-Depth-Anything-Large-MLX
- **License**: cc-by-nc-4.0
- **Parameters**: 384.6M
- **Tags**: mlx, depth-estimation, video-depth-anything
- **Downloads**: 4
- **Stars**: 0
- **Last updated**: 2026-09-01

Source: https://www.modelscope.cn/models/mlx-community/Metric-Video-Depth-Anything-Large-MLX

---

# Metric Video Depth Anything Large (MLX)

MLX port of [Video Depth Anything](https://github.com/DepthAnything/Video-Depth-Anything) (ByteDance, CVPR 2025 highlight): consistent monocular depth estimation for arbitrarily long videos. Converted from the official checkpoint [`depth-anything/Metric-Video-Depth-Anything-Large`](https://huggingface.co/depth-anything/Metric-Video-Depth-Anything-Large).

Architecture: DINOv2 backbone + DPT head with AnimateDiff-style temporal motion modules. Outputs per-frame depth maps, not text.

## Usage

```python
from mlx_vlm import load
from mlx_vlm.models.video_depth_anything.generate import (
    VideoDepthPredictor,
    read_video_frames,
)

model, processor = load("mlx-community/Metric-Video-Depth-Anything-Large-MLX")
predictor = VideoDepthPredictor(model, processor)

frames, fps = read_video_frames("input.mp4", max_len=300, target_fps=15)
depths = predictor.infer(frames)  # (T, H, W) float32
```

## Notes

- Inputs are channel-last `(B, T, H, W, 3)`; H and W must be multiples of 14.
- Metric model: yes. Metric models output absolute depth (meters) and skip scale/shift window alignment.
- Weights are fp32. On GPU, output matches the PyTorch reference to ~1% relative (Metal fast-math); on CPU to ~1e-5.

## License

CC-BY-NC-4.0 (same as the source checkpoint). Non-commercial use only.