Topaz Image Restore

Topaz Image Restore

Playground

Try it on WaveSpeedAI!

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, PNG, or TIFF based on your workflow needs.


Parameters

ParameterRequiredDescription
imageYesSource image to restore (upload or URL)
modelNoRestoration model to use (default: Dust-Scratch)
output_formatNoOutput format: jpeg, jpg, png, tiff, or tif

Model Options

ModelDescription
Dust-ScratchStandard dust and scratch removal (default)
Dust-Scratch V2Improved version with better detection and removal

Output Format Options

  • jpeg / jpg — Compressed format, smaller file size
  • png — Lossless format, supports transparency
  • tiff / tif — Professional format, highest quality preservation

How to Use

  1. Upload your image — drag and drop or paste a URL.
  2. Select model — choose Dust-Scratch or 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

ItemCost
Per image$0.15

Simple flat-rate pricing regardless of image size or model selected.


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 TIFF to preserve maximum quality.
  • 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.

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",
  "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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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

ParameterTypeRequiredDefaultRangeDescription
imagestringNo-The image file to be processed. Supported formats (png jpg jpeg tiff tif)
modelstringNoDust-ScratchDust-Scratch, Dust-Scratch V2The restore model to use. Dust-Scratch: Remove dust and scratches from old photos. Dust-Scratch V2: Enhanced dust and scratch removal with better detail preservation.
output_formatstringNojpegjpeg, jpg, png, tiff, tifThe format of the output image.
enable_base64_outputbooleanNofalse-If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.