> ## 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.

# Frequently Asked Questions

> Common questions and troubleshooting for Real-ESRGAN

Find answers to common questions about using Real-ESRGAN, including model selection, face enhancement, and error resolution.

## Model Selection

<Accordion title="How do I select the right model for my use case?">
  Different models are optimized for different types of content:

  * **RealESRGAN\_x4plus**: General purpose model for real-world images
  * **RealESRGAN\_x4plus\_anime\_6B**: Optimized for anime and illustration images
  * **RealESRGANv2-animevideo-xsx2**: For anime videos at 2x upscaling
  * **RealESRGANv2-animevideo-xsx4**: For anime videos at 4x upscaling
  * **RealESRNet\_x4plus**: Suitable when you want less texture enhancement

  For detailed model comparisons and recommendations, refer to the [Model Zoo](/models/model-zoo) documentation.
</Accordion>

## Face Enhancement

<Accordion title="Can I use face_enhance for anime images or animation videos?">
  <Warning>
    The `face_enhance` option is **only designed for real human faces** and should not be used for anime content.
  </Warning>

  The face enhancement feature uses models trained specifically on real human faces and will not work properly on anime characters or illustrations. Using this option on anime content will:

  * Waste GPU memory unnecessarily
  * Not improve the output quality
  * Potentially introduce artifacts

  **Recommendation**: Omit the `--face_enhance` flag when processing anime images or animation videos to save GPU memory and avoid potential issues.
</Accordion>

## Common Errors

<Accordion title="Error: slow_conv2d_cpu not implemented for Half">
  This error occurs when running Real-ESRGAN inference on CPU with half precision (fp16), which is the default setting for memory efficiency.

  ### Error Message

  ```
  RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'
  ```

  ### Cause

  Real-ESRGAN uses half precision (fp16) by default to:

  * Reduce GPU memory consumption
  * Speed up inference

  However, some operators for half precision inference are not implemented in CPU mode.

  ### Solution

  Add the `--fp32` option to your command to use full precision (fp32) instead:

  ```bash theme={null}
  python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs --fp32
  ```

  Or with the executable:

  ```bash theme={null}
  ./realesrgan-ncnn-vulkan -i input.jpg -o output.png --fp32
  ```

  <Note>
    Using `--fp32` will increase memory usage but is required for CPU inference.
  </Note>
</Accordion>

<Accordion title="Out of memory errors during inference">
  If you encounter GPU out-of-memory errors, try these solutions:

  1. **Use tile mode**: Process the image in smaller tiles
     ```bash theme={null}
     python inference_realesrgan.py -n RealESRGAN_x4plus -i input.jpg --tile 200
     ```

  2. **Disable face enhancement** (if enabled):
     ```bash theme={null}
     python inference_realesrgan.py -n RealESRGAN_x4plus -i input.jpg
     # Remove --face_enhance flag
     ```

  3. **Reduce tile size**: Lower the tile parameter value
     ```bash theme={null}
     python inference_realesrgan.py -n RealESRGAN_x4plus -i input.jpg --tile 100
     ```

  <Note>
    Smaller tile sizes use less memory but may take longer to process.
  </Note>
</Accordion>

## Installation Issues

<Accordion title="How do I verify my installation is working correctly?">
  After installing Real-ESRGAN, test your installation with a simple command:

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

  If you see output images generated without errors, your installation is working correctly.

  For dependency issues, ensure you have:

  * Python 3.7+
  * PyTorch 1.7+
  * basicsr
  * facexlib (if using face enhancement)
  * gfpgan (if using face enhancement)
</Accordion>

<Accordion title="Which Python version should I use?">
  Real-ESRGAN is compatible with **Python 3.7 or higher**.

  Check your Python version:

  ```bash theme={null}
  python --version
  ```

  If you have multiple Python versions installed, you may need to use `python3` explicitly:

  ```bash theme={null}
  python3 inference_realesrgan.py -n RealESRGAN_x4plus -i inputs
  ```
</Accordion>

## Performance

<Accordion title="How can I improve inference speed?">
  Several options can improve Real-ESRGAN's inference speed:

  1. **Use GPU acceleration**: Ensure CUDA is properly installed

  2. **Use the ncnn implementation**: Faster for CPU inference
     ```bash theme={null}
     ./realesrgan-ncnn-vulkan -i input.jpg -o output.png
     ```

  3. **Disable unnecessary features**:
     * Remove `--face_enhance` if not needed
     * Use appropriate tile sizes (larger = faster but more memory)

  4. **Choose the right model**: Smaller models like RealESRGANv2 variants may be faster

  <Note>
    The ncnn implementation offers better performance on both CPU and mobile devices.
  </Note>
</Accordion>