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 110+ image, video, audio and language models.
- Original model & weights: https://github.com/xinntao/Real-ESRGAN
- Authors: Xintao Wang et al. (Tencent ARC Lab)
- License: BSD-3-Clause
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 a low-resolution image, get a sharper, larger one back.
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 https://apimodels.app, then:
# 1) upload the image -> public URL
curl -X POST https://api.apimodels.app/v1/files \
-H "Authorization: Bearer YOUR_API_KEY" -F "file=@input.jpg;type=image/jpeg"
# 2) upscale it
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": "<publicUrl>" }'
# 3) poll GET /v1/images/generations?task_id=... until state == "completed"
Pricing
| Tier | Price |
|---|---|
| real-esrgan | $0.004 / image (flat) |
Failed jobs are not charged. Result files are kept for 7 days.
Links
- Run it: apimodels.app
- Original model: https://github.com/xinntao/Real-ESRGAN
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
