---
license: cc-by-nc-sa-4.0
pipeline_tag: image-to-image
library_name: onnx
tags:
  - image-to-image
  - manga
  - colorization
  - anime
  - gan
  - computer-vision
---
# Manga Light Colorizer — ONNX Inference
Standalone inference script for the Manga Light Colorizer model.

## Gallery

The following gallery uses the **same source images** as the [manga-colorization-v2](https://github.com/qweasdd/manga-colorization-v2) project to facilitate direct comparison between models.

Comparison between input (left) and colorized output (right):

| Input (BW) | Colorized Output |
|------------|------------------|
| <img src="input/bw1.jpg" width="512"> | <img src="output/bw1.jpg" width="512"> |
| <img src="input/bw2.jpg" width="512"> | <img src="output/bw2.jpg" width="512"> |
| <img src="input/bw3.jpg" width="512"> | <img src="output/bw3.jpg" width="512"> |
| <img src="input/bw4.jpg" width="512"> | <img src="output/bw4.jpg" width="512"> |
| <img src="input/bw5.jpg" width="512"> | <img src="output/bw5.jpg" width="512"> |
| <img src="input/bw6.jpg" width="512"> | <img src="output/bw6.jpg" width="512"> |

## Quick Start

```bash
# Install dependencies
pip install -r requirements.txt

# Single image
python inference.py --input input/bw1.jpg

# All images in a folder
python inference.py --input input/

# Custom output folder
python inference.py --input input/ --output_dir output/

# Custom inference resolution
python inference.py --input input/ --infer-size 1024
```

## Arguments

| Argument | Required | Default | Description |
|----------|----------|---------|-------------|
| `--input` | Yes | - | Input grayscale image or folder |
| `--onnx-model` | No | `models/v6_generator.onnx` | Generator ONNX model path |
| `--sam-onnx` | No | `models/v6_sam_encoder.onnx` | SAM 2.1 encoder ONNX path |
| `--output_dir` | No | `./output/` | Output folder for colorized images |
| `--infer-size` | No | `768` | Inference resolution (square) |
| `--ort-device` | No | `cpu` | ONNX Runtime device (`cpu` or `cuda`) |

## Model Information

- **Architecture**: FastViT-SA36 Encoder + DualSemanticSAM Guide + UNet V6 Decoder
- **Training Resolution**: 512×512 pixels
- **Current Inference Resolution**: 768×768 pixels (default)
- **Output**: Resized back to original input resolution

### Important: Resolution Notice

> The model was trained at **512×512 pixels**. Inference currently runs at **768×768 pixels** by default.
>
> **More the inference resolution differs from 512×512, the less faithful the colors will be.**
>
> For best results, use the training resolution:
> ```bash
> # Best color accuracy, but lower resolution — matches training resolution
> python inference.py --input input/ --infer-size 512
>
> # Default (good quality)
> python inference.py --input input/
>
> # Higher resolution (may reduce color accuracy)
> python inference.py --input input/ --infer-size 1024
> ```

## Pipeline

```
Input (grayscale) → Resize to infer-size → SAM 2.1 (zeros) → Generator ONNX → Resize to original
```

## Requirements

- Python 3.10+
- onnxruntime
- numpy
- opencv-python

See [`requirements.txt`](requirements.txt) for full list.

## License

### Model Weights
Licensed under **CC BY-NC-SA 4.0** (Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International).

[![CC BY-NC-SA 4.0](https://licensebuttons.net/l/by-nc-sa/4.0/88x31.png)](https://creativecommons.org/licenses/by-nc-sa/4.0/)

You may:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material

Under the following terms:
- **Attribution** — You must give appropriate credit
- **NonCommercial** — You may not use the material for commercial purposes
- **ShareAlike** — If you remix, transform, or build upon the material, you must distribute your contributions under the same license

See: https://creativecommons.org/licenses/by-nc-sa/4.0/

### Inference Code
Licensed under **GNU General Public License v3** (GPL-3.0).

[![GPL v3](https://www.gnu.org/graphics/gplv3-127x51.png)](https://www.gnu.org/licenses/gpl-3.0.html)

You may use, modify, and distribute this code under the terms of the GPL-3.0 license.

See: https://www.gnu.org/licenses/gpl-3.0.html