Basic Inference

Learn how to use Real-ESRGAN for image super-resolution with the inference_realesrgan.py script

Overview

The inference_realesrgan.py script is the main tool for performing image super-resolution with Real-ESRGAN. It supports various models, configurations, and advanced features like face enhancement and tile processing.

Quick Start

1. Basic Usage

   Run Real-ESRGAN with default settings:

   python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs
   

   This will process all images in the inputs folder using the RealESRGAN_x4plus model and save results to the results folder.

2. Custom Output

   Specify input and output paths:

   python inference_realesrgan.py -n RealESRGAN_x4plus -i input.jpg -o output_folder
   
3. View Results

   Enhanced images will be saved with the _out suffix by default (e.g., image_out.png).

Command-Line Arguments

Required Arguments

-i, --input · string · default: "inputs"

Input image file or folder containing images to process

-n, --model_name · string · default: "RealESRGAN_x4plus"

Model to use for super-resolution. Available models:

• RealESRGAN_x4plus - General purpose 4x upscaling
• RealESRNet_x4plus - ESRGAN model without GAN
• RealESRGAN_x4plus_anime_6B - Optimized for anime images
• RealESRGAN_x2plus - 2x upscaling model
• realesr-animevideov3 - Anime video model (XS size)
• realesr-general-x4v3 - General purpose with denoise control

Output Options

-o, --output · string · default: "results"

Output folder for enhanced images

-s, --outscale · float · default: "4"

Final upsampling scale of the image. Can be any value (e.g., 3.5).

The model performs its native upscaling, then resizes to the target scale using LANCZOS4 interpolation.

--suffix · string · default: "out"

Suffix added to restored images (e.g., image_out.png). Set to empty string for no suffix.

--ext · string · default: "auto"

Output image format: auto, jpg, or png

• auto: Uses the same extension as input
• RGBA images are always saved as PNG

Performance Options

-t, --tile · integer · default: "0"

Tile size for processing large images. Set to 0 to disable tiling.

Use tiling if you encounter CUDA out of memory errors. Recommended values: 256, 400, or 512.

python inference_realesrgan.py -n RealESRGAN_x4plus -i input.jpg --tile 400

--tile_pad · integer · default: "10"

Padding size for each tile to reduce edge artifacts

--pre_pad · integer · default: "0"

Pre-padding size at each border of the image

--fp32 · flag

Use FP32 (full precision) instead of FP16 (half precision) during inference

Increases memory usage but may improve quality slightly. Default is FP16.

-g, --gpu-id · integer · default: "None"

GPU device to use (e.g., 0, 1, 2 for multi-GPU systems)

Advanced Options

--face_enhance · flag

Enable GFPGAN face enhancement integration

Automatically enhances faces in the image using GFPGAN v1.3

python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs --face_enhance

-dn, --denoise_strength · float · default: "0.5"

Denoise strength for the realesr-general-x4v3 model only

• 0: Weak denoise (keep noise)
• 1: Strong denoise ability
• Values between 0 and 1 interpolate between the two extremes

--model_path · string · default: "None"

Custom model path. Usually not needed as models are auto-downloaded to the weights folder.

--alpha_upsampler · string · default: "realesrgan"

Upsampler for alpha channels in RGBA images: realesrgan or bicubic

Common Usage Examples

Example 1: Basic Upscaling

python inference_realesrgan.py -n RealESRGAN_x4plus -i input.jpg

Example 2: Custom Scale with Face Enhancement

python inference_realesrgan.py -n RealESRGAN_x4plus -i input.jpg --outscale 3.5 --face_enhance

Example 3: Batch Processing with Tiling

python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs_folder -o results --tile 400 --tile_pad 10

Example 4: Denoise Control

python inference_realesrgan.py -n realesr-general-x4v3 -i input.jpg --denoise_strength 0.8

Model Downloads

Models are automatically downloaded on first use. Manual download URLs:

RealESRGAN_x4plus

wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P weights

RealESRNet_x4plus

wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth -P weights

RealESRGAN_x2plus

wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth -P weights

realesr-general-x4v3

wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P weights
wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth -P weights

Error Handling

CUDA Out of Memory Error

If you encounter this error:

RuntimeError: CUDA out of memory

Try the following solutions:

1. Use the --tile option with a smaller value (e.g., 256 or 400)
2. Enable --fp32 if using half precision
3. Use a smaller --outscale value
4. Process images one at a time instead of batch processing

Supported Image Formats

The inference script supports:

• Color spaces: RGB, RGBA (with alpha channel), Grayscale
• Bit depths: 8-bit, 16-bit images
• Formats: JPG, PNG, WebP, and other common formats

Next Steps

General Images

Learn model selection for real-world photos

Anime Images

Optimize for anime and illustration content

Face Enhancement

Integrate GFPGAN for better face restoration

Video Processing

Process video files frame by frame