Upscaling

Real Esrgan UpscalerAPI

Real-ESRGAN is an open-source AI-powered image restoration and super-resolution model designed to upscale low-resolution images by – while removing noise, compression artifacts, and restoring fine details. It is particularly effective for real-world images, including photos, anime, and graphics, often employing U-Net discriminators to create sharp, high-fidelity outputs.

Test in Dashboard View Docs ← All Tools

Three ways to use this tool

REST API

One POST request. Get the result back directly — as an image, video, or JSON depending on the tool.

terminal

curl -X POST https://apiai.me/api/workflow/real-esrgan \
     -H "X-API-Key: YOUR_API_KEY" \
     -F "image=@input.jpg" \
     -F "face_enhance=false" \
     -F "sample_percent=10" \
     -F "scale=4" \
     -F "threshold=250"
     --output result.png

Dashboard Playground

Test this tool visually before writing any code. Upload an image, set parameters, and see the result live. When it looks right, copy the auto-generated curl command and paste it into your app.

Open the dashboard → API Toolbox
Find Real Esrgan Upscaler and click it
Upload your input and adjust parameters
Copy the curl command and ship

Open Dashboard →

Batch Processing

Process hundreds of images at once without writing a loop. Upload a CSV with one row per item, set your parameters, and download the results as a ZIP when they're done.

Open the dashboard → Batches
Select Real Esrgan Upscaler
Add your content and start the batch
Download results ZIP when complete

Go to Batches →

Parameters

Name	Required	Description	Default / Options
`face_enhance`	optional	Run GFPGAN face enhancement along with upscaling	`false`
`sample_percent`	optional	% of edge pixels that must be transparent (default: 10)	`10`
`scale`	optional	Factor to scale image by	`4`
`threshold`	optional	Alpha threshold for	`250`