> ## 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.

# Model Zoo

> Complete collection of Real-ESRGAN models for different use cases

Real-ESRGAN provides a comprehensive collection of pre-trained models optimized for different types of content. Choose the right model based on your input type and requirements.

## Model Categories

<CardGroup cols={3}>
  <Card title="General Models" icon="image" href="/models/general-models">
    Models optimized for general photographic images
  </Card>

  <Card title="Anime Models" icon="sparkles" href="/models/anime-models">
    Specialized models for anime images and illustrations
  </Card>

  <Card title="Video Models" icon="film" href="/models/video-models">
    Lightweight models designed for video upscaling
  </Card>
</CardGroup>

## Quick Reference

### General Images

| Model                | Scale | Use Case                         |
| -------------------- | ----- | -------------------------------- |
| RealESRGAN\_x4plus   | 4x    | Best quality for general images  |
| RealESRGAN\_x2plus   | 2x    | General images with 2x upscaling |
| realesr-general-x4v3 | 1x-4x | Lightweight, fast processing     |
| RealESRNet\_x4plus   | 4x    | MSE loss (smoother results)      |

### Anime Content

| Model                         | Scale | Use Case                       |
| ----------------------------- | ----- | ------------------------------ |
| RealESRGAN\_x4plus\_anime\_6B | 4x    | Anime images and illustrations |
| realesr-animevideov3          | 1x-4x | Anime videos (lightweight)     |

## Model Selection Guide

<AccordionGroup>
  <Accordion title="For General Photography">
    Use **RealESRGAN\_x4plus** for the best quality on natural images, photographs, and general content. This is the flagship model with 23 RRDB blocks.

    If you need faster processing or have limited GPU memory, try **realesr-general-x4v3**, which is a compact model that still delivers good results.
  </Accordion>

  <Accordion title="For Anime/Manga">
    Use **RealESRGAN\_x4plus\_anime\_6B** for anime images and illustrations. This model is optimized specifically for anime characteristics and uses only 6 RRDB blocks for efficiency.

    For anime videos, use **realesr-animevideov3**, which is designed for temporal consistency and fast processing.
  </Accordion>

  <Accordion title="For Video Processing">
    Video processing requires models that balance quality with speed. Use:

    * **realesr-animevideov3** for anime videos
    * **realesr-general-x4v3** for general video content

    Both models support variable scaling (1x, 2x, 3x, 4x) and have compact architectures for efficient processing.
  </Accordion>

  <Accordion title="For Smooth Results">
    If you prefer smoother, less sharp results (useful for certain artistic styles), use **RealESRNet\_x4plus**. This model is trained with MSE loss, producing over-smooth effects compared to GAN-based models.
  </Accordion>
</AccordionGroup>

<Note>
  **Discriminator Models**: Models ending with `_netD` are discriminator networks used for fine-tuning. You typically don't need these for inference.
</Note>

## Download Locations

All models are hosted on GitHub Releases:

```bash theme={null}
https://github.com/xinntao/Real-ESRGAN/releases
```

Models are automatically downloaded when using the inference scripts with the `-n` parameter:

```bash theme={null}
python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs
```

## Next Steps

<CardGroup cols={3}>
  <Card title="General Models" icon="image" href="/models/general-models">
    Detailed specifications and usage
  </Card>

  <Card title="Anime Models" icon="sparkles" href="/models/anime-models">
    Anime-specific optimizations
  </Card>

  <Card title="Video Models" icon="film" href="/models/video-models">
    Video processing workflows
  </Card>
</CardGroup>