Real-ESRGAN β€” hosted API access

This repository is not the model weights β€” it documents running Real-ESRGAN through a hosted API on apimodels.app, a multi-model gateway where one key and one OpenAI-compatible endpoint reach 170+ image, video, audio and language models.

Independent hosted-API integration. Not affiliated with or endorsed by the authors; does not redistribute their weights. All credit for the model is theirs.

What it does

The classic open image upscaler. Send an image (no prompt) and get it back enlarged by scale (1–10, default 4), with optional GFPGAN face enhancement. It works best on illustration, anime and hand-drawn or painted artwork, where lines stay crisp and flat areas stay clean. On real photos it enlarges but does not repair blur, damage or noise. Inputs larger than about 2.1 megapixels are scaled down proportionally to fit before upscaling.

Real-ESRGAN β€” hosted API access sample

Left: low-resolution input. Right: the upscaled result.

Use it via API

On apimodels.app the model is served as real-esrgan. Get a key at apimodels.app, then:

# 1) upload the image -> public URL (skip this if the image already has a public URL)
curl -X POST https://api.apimodels.app/v1/files \
  -H "Authorization: Bearer YOUR_API_KEY" -F "file=@input.jpg;type=image/jpeg"
# -> { "data": { "publicUrl": "https://r2.apimodels.app/uploads/.../input.jpg" } }
# 2) upscale it (async)
curl -X POST https://api.apimodels.app/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" \
  -d '{ "model": "real-esrgan", "image_url": "<publicUrl>", "scale": 4, "face_enhance": false }'
# -> { "data": { "taskId": "...", "state": "pending" } }
# 3) poll GET /v1/images/generations?task_id=... until state == "completed", then read resultUrls[0]

Fields: image_url (public http(s) URL), scale (1–10, default 4), face_enhance (default false), optional callback_url.

Pricing

Tier Price
real-esrgan $0.005 / image (flat, any scale, face enhance included)

Failed jobs are not charged. Result files are kept for 30 days; download anything you want to keep.

Links

More browser demos, a dataset and API guides: apimodels.app API demos collection

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Collection including stimi/real-esrgan-api