> ## 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.

# General Models

> Models optimized for general photographic images and natural scenes

General models are designed for natural images, photographs, and real-world content. These models excel at upscaling portraits, landscapes, and everyday photography.

## Available Models

<CardGroup cols={2}>
  <Card title="RealESRGAN_x4plus" icon="star">
    Primary model with best quality for 4x upscaling
  </Card>

  <Card title="RealESRGAN_x2plus" icon="expand">
    Optimized for 2x upscaling
  </Card>

  <Card title="realesr-general-x4v3" icon="gauge-high">
    Lightweight model for fast processing
  </Card>

  <Card title="RealESRNet_x4plus" icon="paintbrush">
    MSE-based model for smooth results
  </Card>
</CardGroup>

## Model Specifications

### RealESRGAN\_x4plus

<Note>
  **Recommended**: This is the flagship model for general images, providing the best quality for 4x upscaling.
</Note>

| Property            | Value                                                                                                           |
| ------------------- | --------------------------------------------------------------------------------------------------------------- |
| **Scale**           | 4x                                                                                                              |
| **Architecture**    | RRDBNet                                                                                                         |
| **RRDB Blocks**     | 23                                                                                                              |
| **Features**        | 64                                                                                                              |
| **Growth Channels** | 32                                                                                                              |
| **Download**        | [RealESRGAN\_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth) |

```bash theme={null}
# Download and use
wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P weights
python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs -o outputs
```

### RealESRGAN\_x2plus

| Property            | Value                                                                                                           |
| ------------------- | --------------------------------------------------------------------------------------------------------------- |
| **Scale**           | 2x                                                                                                              |
| **Architecture**    | RRDBNet                                                                                                         |
| **RRDB Blocks**     | 23                                                                                                              |
| **Features**        | 64                                                                                                              |
| **Growth Channels** | 32                                                                                                              |
| **Download**        | [RealESRGAN\_x2plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth) |

```bash theme={null}
# Download and use
wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth -P weights
python inference_realesrgan.py -n RealESRGAN_x2plus -i inputs -o outputs
```

### realesr-general-x4v3

<Note>
  **Lightweight**: This model consumes much less GPU memory and processing time, making it ideal for resource-constrained environments.
</Note>

| Property               | Value                                                                                                                  |
| ---------------------- | ---------------------------------------------------------------------------------------------------------------------- |
| **Scale**              | 1x, 2x, 3x, or 4x (variable)                                                                                           |
| **Architecture**       | SRVGGNetCompact                                                                                                        |
| **Convolution Layers** | 32                                                                                                                     |
| **Features**           | 64                                                                                                                     |
| **Size**               | Small (S)                                                                                                              |
| **Download**           | [realesr-general-x4v3.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth) |

```bash theme={null}
# Download and use with custom scale
wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P weights
python inference_realesrgan.py -n realesr-general-x4v3 -i inputs -s 2  # 2x upscaling
```

<Accordion title="Denoise Strength Control">
  The `realesr-general-x4v3` model supports adjustable denoise strength:

  ```bash theme={null}
  # Weak denoise (keep more original texture)
  python inference_realesrgan.py -n realesr-general-x4v3 -i inputs -dn 0.2

  # Strong denoise (smoother result)
  python inference_realesrgan.py -n realesr-general-x4v3 -i inputs -dn 0.8
  ```

  The `-dn` parameter ranges from 0 (weak denoise) to 1 (strong denoise). Default is 0.5.
</Accordion>

### RealESRNet\_x4plus

<Note>
  This model uses MSE loss instead of GAN training, resulting in over-smooth effects. Use this if you prefer less sharp, more natural-looking results.
</Note>

| Property          | Value                                                                                                           |
| ----------------- | --------------------------------------------------------------------------------------------------------------- |
| **Scale**         | 4x                                                                                                              |
| **Architecture**  | RRDBNet                                                                                                         |
| **RRDB Blocks**   | 23                                                                                                              |
| **Training Loss** | MSE (no GAN)                                                                                                    |
| **Download**      | [RealESRNet\_x4plus.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth) |

```bash theme={null}
wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth -P weights
python inference_realesrgan.py -n RealESRNet_x4plus -i inputs -o outputs
```

## Legacy Model

### ESRGAN (Official)

The original ESRGAN model trained on DF2K and OST datasets:

| Property     | Value                                                                                                                                                     |
| ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Scale**    | 4x                                                                                                                                                        |
| **Download** | [ESRGAN\_SRx4\_DF2KOST\_official-ff704c30.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth) |

## Discriminator Models

<Note>
  Discriminator models are used for fine-tuning and training. You don't need these for inference.
</Note>

| Discriminator                                                                                                                | Corresponding Generator Model |
| ---------------------------------------------------------------------------------------------------------------------------- | ----------------------------- |
| [RealESRGAN\_x4plus\_netD.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x4plus_netD.pth) | RealESRGAN\_x4plus            |
| [RealESRGAN\_x2plus\_netD.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.3/RealESRGAN_x2plus_netD.pth) | RealESRGAN\_x2plus            |

## Model Comparison

### Quality vs Speed

```
Quality:  RealESRGAN_x4plus > RealESRGAN_x2plus > realesr-general-x4v3 > RealESRNet_x4plus
Speed:    realesr-general-x4v3 > RealESRNet_x4plus > RealESRGAN_x2plus > RealESRGAN_x4plus
Memory:   realesr-general-x4v3 < RealESRNet_x4plus < RealESRGAN_x2plus < RealESRGAN_x4plus
```

### Use Case Recommendations

<CardGroup cols={2}>
  <Card title="Best Quality" icon="star">
    **RealESRGAN\_x4plus**

    Use for final production work where quality is paramount.
  </Card>

  <Card title="Fast Processing" icon="bolt">
    **realesr-general-x4v3**

    Use for batch processing or when speed matters.
  </Card>

  <Card title="2x Upscaling" icon="expand">
    **RealESRGAN\_x2plus**

    Use when you only need 2x resolution increase.
  </Card>

  <Card title="Smooth Results" icon="paintbrush">
    **RealESRNet\_x4plus**

    Use for artistic or stylized results without sharpening.
  </Card>
</CardGroup>

## Usage Examples

### Basic Inference

```bash theme={null}
# Using RealESRGAN_x4plus (recommended)
python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs

# Using lightweight model
python inference_realesrgan.py -n realesr-general-x4v3 -i inputs

# Custom output scale
python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs -s 2  # 2x instead of 4x
```

### Advanced Options

```bash theme={null}
# With tiling for large images
python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs -t 400

# With face enhancement
python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs --face_enhance

# Custom output folder and format
python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs -o results --ext jpg
```

## Next Steps

<CardGroup cols={2}>
  <Card title="Anime Models" icon="sparkles" href="/models/anime-models">
    Learn about anime-specific models
  </Card>

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