Topaz Image Restore API Documentation

Topaz Image Restore API Documentation

Playground

Topaz Image Restore enhances older and poorer quality photos through restoration. Remove dust, scratches, and damage from vintage photos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Topaz Image Restore is a professional-grade image restoration model powered by Topaz Labs’ AI technology. Upload your image and let AI automatically detect and remove dust, scratches, and other imperfections — perfect for restoring old photos and scanned images.

Why Choose This?

• Dust and scratch removal AI automatically detects and removes dust particles, scratches, and other surface imperfections.

• Old photo restoration Ideal for restoring scanned photos, film negatives, and vintage images.

• Professional quality Powered by Topaz Labs’ AI, trusted by professional photographers and archivists.

• Multiple output formats Export as JPEG or PNG based on your workflow needs.

Parameters

Model Options

Output Format Options

• jpeg — Compressed format, smaller file size
• png — Lossless format, supports transparency

How to Use

1. Upload your image — drag and drop or paste a URL.
2. Select model — use Dust-Scratch V2.
3. Choose output format — select based on your quality and file size needs.
4. Run — submit and download the restored image.

Pricing

The minimum charge is $0.096. Each additional started 24-megapixel block adds $0.096.

Best Use Cases

• Old Photo Restoration — Remove dust and scratches from vintage photographs.
• Film Scanning — Clean up scanned film negatives and slides.
• Archive Digitization — Restore historical images for digital archives.
• Family Photos — Bring old family photos back to life.
• Print Restoration — Clean up scanned prints with surface damage.

Pro Tips

• Use Dust-Scratch V2 for better results on heavily damaged images.
• For archival work, export as PNG to avoid additional compression artifacts.
• Combine with other Topaz tools (Sharpen, Upscale) for complete restoration workflow.
• Best results come from high-resolution scans of the original photos.

Notes

• This model is optimized for dust and scratch removal, not for colorization or major damage repair.
• For best results, scan original photos at high resolution before processing.
• V2 model generally produces better results but may take slightly longer.

Related Models

• Topaz Image Sharpen — AI-powered image sharpening.
• Topaz Image Denoise — AI-powered noise reduction.

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'
{
  "model": "Dust-Scratch V2",
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/topaz/image/restore" \
  -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