Clarity AI Pro Upscaler API Documentation

Clarity AI Pro Upscaler API Documentation

Playground

Clarity Pro Upscaler is a photorealistic image upscaler from Clarity AI with identity preservation, creative detail control, and up to 16x scaling. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Clarity AI Pro Upscaler upscales images with Clarity AI while exposing a simple target_megapixels control for predictable output sizing. Scaling settings are selected automatically so the final image lands close to the requested megapixel target.

Why Choose This?

• Predictable output sizing Set the desired output directly with target_megapixels for easier delivery planning and cost control.

• Simple enhancement workflow Upload an image, choose the target megapixels, optionally adjust creativity, and generate the result.

• Flexible restoration strength Use creativity to balance stricter source preservation against stronger generated detail.

• Reliable output delivery Generated images are delivered via the WaveSpeed CDN for fast preview and download.

• Modern Clarity AI pipeline Powered by the latest Clarity AI upscaling technology.

Parameters

How to Use

1. Upload your image — paste a URL or upload the source image.
2. Choose target megapixels — select the output size that matches your delivery needs.
3. Adjust creativity (optional) — lower values keep the result stricter to the source, while higher values add more generated detail.
4. Submit — run the model and download the upscaled image.

Quick Sizing Guide

• 4 MP — fast testing and lightweight output
• 8–16 MP — high-quality web, e-commerce, and standard print assets
• 25 MP+ — large-format delivery and premium output needs

Pricing

Pricing is based on the requested target_megapixels.

• Rate: $0.03 per target megapixel

Example Costs

Billing Rules

• Pricing scales linearly with target_megapixels
• Each additional megapixel adds $0.03
• creativity does not affect pricing

Best Use Cases

• Photo enhancement — improve resolution while preserving structure and natural detail
• E-commerce assets — prepare sharper product images for listings, ads, and catalogs
• Creative delivery — generate larger outputs for campaigns, presentations, and design workflows
• Print preparation — produce higher-resolution assets for brochures, posters, and other print use
• AI image cleanup — refine generated images into cleaner, more usable high-resolution outputs

Pro Tips

• Start with a smaller megapixel target first, then increase only when you need a larger final output.
• Keep creativity lower when identity, structure, or product accuracy matters most.
• Increase creativity gradually if you want stronger generated texture or sharper enhancement.
• Use the cleanest source image available for better detail recovery.

Notes

• The input may be resized before upscaling so the output stays close to the requested target_megapixels.
• Clean, high-quality inputs generally produce the best results.
• Output size is controlled by the requested megapixel target rather than a fixed resolution tier.

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",
  "target_megapixels": 4,
  "creativity": 0
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/clarity-ai/pro-upscaler" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters