> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/xinntao/Real-ESRGAN/llms.txt
> Use this file to discover all available pages before exploring further.

# Anime Images

> Upscale anime illustrations and artwork with the optimized RealESRGAN_x4plus_anime_6B model

## Overview

Real-ESRGAN provides a specialized model optimized for anime images, illustrations, and artwork. The `RealESRGAN_x4plus_anime_6B` model is significantly smaller than the general model while delivering excellent results for anime content.

## RealESRGAN\_x4plus\_anime\_6B Model

### Key Features

* **Optimized for Anime**: Trained specifically on anime and illustration data
* **Smaller Size**: Only 6 RRDB blocks vs. 23 blocks in the general model (\~17MB vs \~64MB)
* **Fast Processing**: Faster inference due to smaller architecture
* **High Quality**: Preserves anime-style details and aesthetics

### Download and Install

<Steps>
  <Step title="Download Model">
    ```bash theme={null}
    wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P weights
    ```
  </Step>

  <Step title="Run Inference">
    ```bash theme={null}
    python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i inputs
    ```
  </Step>

  <Step title="Check Results">
    Enhanced anime images are saved in the `results` folder with 4x upscaling.
  </Step>
</Steps>

## Usage Examples

### Basic Upscaling

<CodeGroup>
  ```bash Single Image theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime_image.jpg
  ```

  ```bash Batch Processing theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime_folder -o results
  ```

  ```bash Custom Output Scale theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.png --outscale 2
  ```

  ```bash PNG Output theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg --ext png
  ```
</CodeGroup>

### Advanced Options

<CodeGroup>
  ```bash With Tiling (Large Images) theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i large_anime.png --tile 400
  ```

  ```bash Custom Suffix theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg --suffix upscaled
  # Output: anime_upscaled.jpg
  ```

  ```bash FP32 Precision theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.png --fp32
  ```
</CodeGroup>

## Model Specifications

| Property             | Value                          |
| -------------------- | ------------------------------ |
| **Architecture**     | RRDBNet with 6 blocks          |
| **Upscale Factor**   | 4x                             |
| **Model Size**       | \~17MB                         |
| **Input Channels**   | 3 (RGB)                        |
| **Output Channels**  | 3 (RGB)                        |
| **Feature Channels** | 64                             |
| **Growth Channels**  | 32                             |
| **Training Data**    | Anime images and illustrations |

## Comparison with Other Models

<Tabs>
  <Tab title="vs RealESRGAN_x4plus">
    | Feature        | Anime 6B            | x4plus General        |
    | -------------- | ------------------- | --------------------- |
    | Anime Quality  | Excellent           | Good                  |
    | General Images | Good                | Excellent             |
    | Model Size     | 17MB                | 64MB                  |
    | Speed          | Faster              | Slower                |
    | Best For       | Anime/Illustrations | Photos/Natural images |
  </Tab>

  <Tab title="vs waifu2x">
    Real-ESRGAN anime model provides comparable or better quality than waifu2x with these advantages:

    * More accurate detail reconstruction
    * Better handling of compression artifacts
    * Sharper edges and cleaner lines
    * Native PyTorch implementation for GPU acceleration

    See detailed comparisons in the [source documentation](https://github.com/xinntao/Real-ESRGAN/blob/master/docs/anime_model.md).
  </Tab>

  <Tab title="vs realesr-animevideov3">
    | Feature       | Anime 6B      | AnimeVideo v3 |
    | ------------- | ------------- | ------------- |
    | Image Quality | Excellent     | Very Good     |
    | Video Quality | N/A           | Excellent     |
    | Model Size    | 17MB          | \~8MB (XS)    |
    | Best For      | Static images | Video frames  |

    Use `RealESRGAN_x4plus_anime_6B` for static anime images and `realesr-animevideov3` for video processing.
  </Tab>
</Tabs>

## Common Use Cases

### Upscaling Anime Screenshots

```bash theme={null}
python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i screenshots -o upscaled
```

Perfect for enhancing low-resolution anime screenshots from streaming services.

### Processing Manga Panels

```bash theme={null}
python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i manga_pages -o enhanced --ext png
```

Preserves fine line details in manga artwork.

### Enhancing Anime Artwork

```bash theme={null}
python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i artwork.jpg --outscale 4 --ext png
```

Upscale digital artwork and illustrations while maintaining anime aesthetic.

### Processing Game Assets

```bash theme={null}
python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i game_assets -o enhanced_assets --tile 400
```

Upscale anime-style game sprites and textures. Use tiling for large textures.

## Tips for Best Results

<Tip>
  **Image Format**

  Use PNG format for anime images when possible to avoid JPEG compression artifacts:

  ```bash theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i input.jpg --ext png
  ```
</Tip>

<Tip>
  **Transparent Images**

  The anime model handles RGBA images with transparency:

  ```bash theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime_with_alpha.png
  ```

  Output is automatically saved as PNG to preserve the alpha channel.
</Tip>

<Warning>
  **Face Enhancement Not Recommended**

  The `--face_enhance` option is designed for realistic faces and may not work well with anime faces. It's recommended to not use face enhancement with anime models:

  ```bash theme={null}
  # Don't use --face_enhance with anime images
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg
  ```
</Warning>

<Tip>
  **Choosing Output Scale**

  For anime images:

  * **2x**: Moderate enhancement, good for already decent quality
  * **4x**: Standard upscaling for most anime content
  * **Higher**: Use for very low resolution sources

  ```bash theme={null}
  # For moderate quality anime
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg --outscale 2

  # For low quality anime
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg --outscale 4
  ```
</Tip>

## Performance Optimization

### Memory Usage

The anime model uses less memory than the general model:

<CodeGroup>
  ```bash Standard Processing theme={null}
  # No tiling needed for most images
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg
  ```

  ```bash Large Images theme={null}
  # Use tiling for very large images
  python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i large_anime.png --tile 512
  ```
</CodeGroup>

### Batch Processing

Process multiple anime images efficiently:

```bash theme={null}
# Process entire folder
python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime_collection -o upscaled_collection

# With custom settings
python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime_collection \
  -o upscaled_collection --ext png --suffix enhanced
```

### GPU Selection

Use specific GPU for processing:

```bash theme={null}
# Use GPU 0
python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg --gpu-id 0

# Use GPU 1
python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg --gpu-id 1
```

## NCNN Executable Alternative

For users who prefer the portable NCNN executable:

<Steps>
  <Step title="Download NCNN Executable">
    Download the appropriate version for your platform:

    * [Windows](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip)
    * [Linux](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip)
    * [MacOS](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip)
  </Step>

  <Step title="Run NCNN Version">
    ```bash theme={null}
    ./realesrgan-ncnn-vulkan.exe -i anime.jpg -o output.png -n realesrgan-x4plus-anime
    ```
  </Step>
</Steps>

The NCNN version doesn't require CUDA or PyTorch installation.

## Troubleshooting

<AccordionGroup>
  <Accordion title="Results look over-smoothed">
    This is normal for the anime model as it's trained to reduce noise. If you want to preserve more texture:

    1. Use the general model instead:
       ```bash theme={null}
       python inference_realesrgan.py -n RealESRGAN_x4plus -i anime.jpg
       ```

    2. Or use a lower output scale:
       ```bash theme={null}
       python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg --outscale 2
       ```
  </Accordion>

  <Accordion title="Colors look different">
    Ensure you're using PNG output for best color preservation:

    ```bash theme={null}
    python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.jpg --ext png
    ```
  </Accordion>

  <Accordion title="CUDA out of memory">
    Use tiling to reduce memory usage:

    ```bash theme={null}
    python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i anime.png --tile 400
    ```

    Try smaller tile sizes (256, 300) if still encountering issues.
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Anime Videos" icon="video" href="/guides/anime-videos">
    Learn to upscale anime videos with realesr-animevideov3
  </Card>

  <Card title="General Images" icon="image" href="/guides/general-images">
    Explore models for real-world photos
  </Card>

  <Card title="NCNN Executable" icon="rocket" href="/guides/ncnn-executable">
    Use the portable executable without Python
  </Card>
</CardGroup>