Real Esrgan

Real Esrgan

Playground

Real-ESRGAN delivers high-quality image super-resolution with optional face correction and adjustable upscale factors. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Real-ESRGAN is an image upscaling and enhancement model that improves resolution and perceived detail while keeping the original content intact. Upload a low-resolution or slightly blurry image and the model produces a sharper, higher-quality result suitable for publishing, sharing, or downstream generation workflows. It’s commonly used as a final polish step for portraits, product photos, and AI-generated images.

Key capabilities

• Image upscaling (super-resolution) from a single input image
• Enhances perceived sharpness and fine details
• Reduces common low-res artifacts and compression noise
• Works well for portraits, objects, and general photography
• Simple “upload → enhance” workflow

Use cases

• Upscale AI-generated images before posting or printing
• Improve clarity of portraits and faces (light enhancement)
• Enhance product photos for e-commerce listings
• Reduce compression artifacts in web images
• Preprocess inputs for other models that benefit from higher-res images

Pricing

Inputs

• image (required): the image to upscale/enhance

Tips

• Start with already well-exposed images for best results
• If the source is extremely blurry, expect improvement but not full recovery of lost detail
• For stylized images, run a small batch and pick the most natural-looking output

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/real-esrgan" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters