Fuser

ESRGAN Upscaler

Provided by Fal — Learn More

Upscale and enhance images using Real-ESRGAN neural networks.

Preview

Inputs

Image
image

The image to upscale.

Scale Factor
number

The factor by which to upscale the image.

default: 4•minimum: 1•maximum: 8
Tile Size
number

Tile size for processing large images. Set to 0 for no tiling. Use 200-400 if you encounter memory issues.

default: 0•minimum: 0•maximum: 800
Face Enhancement
toggle

Enable special processing for enhancing faces in the image.

default: false
Model
dropdown

The upscaling model to use. Different models are optimized for different types of images.

default: RealESRGAN_x4plusAccepts: Standard (4x upscaling), Standard (2x upscaling), Anime (4x upscaling), V3 (4x upscaling), WDN V3 (4x upscaling), Anime V3 (4x upscaling)
Output Format
dropdown

The file format for the output image.

default: jpegAccepts: PNG (lossless, transparent), JPEG (smaller file size)

Outputs

Upscaled Image
image

The resulting enhanced image.