Topaz Image Denoise

Topaz Image Denoise

Playground

Topaz Image Denoise removes grain and high-ISO noise while preserving detail. Perfect for low-light photography and high-ISO images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Topaz Image Denoise is a professional-grade noise reduction model powered by Topaz Labs’ AI technology. Upload your image and select from multiple denoise strengths — AI intelligently removes noise while preserving detail and texture.

Why Choose This?

• AI-powered noise reduction Intelligently removes noise while preserving important image details and textures.

• Multiple strength levels Choose from Normal, Strong, or Extreme based on your noise level and quality needs.

• Detail preservation Unlike traditional denoise tools, AI preserves edges, textures, and fine details.

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

Parameters

Model Options

Output Format Options

• jpeg / jpg — 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 — choose denoise strength based on noise level.
3. Choose output format — select based on your quality and file size needs.
4. Run — submit and download the denoised image.

Pricing

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

Best Use Cases

• High ISO Photos — Clean up grainy images shot at high ISO settings.
• Low Light Photography — Remove noise from night and indoor photos.
• Video Stills — Clean up frames extracted from video footage.
• Scanned Photos — Reduce grain and noise from scanned film images.
• Smartphone Photos — Improve quality of noisy mobile phone images.

Pro Tips

• Start with Normal for most images — only use Strong or Extreme if needed.
• Over-denoising can make images look plastic — find the right balance.
• Works best when combined with sharpening after denoise.
• For archival quality, export as PNG to avoid additional compression artifacts.

Notes

• Higher strength settings remove more noise but may reduce fine detail.
• Best results come from images with uniform noise patterns.
• For images with both noise and blur, denoise first, then sharpen.

Related Models

• Topaz Image Sharpen — AI-powered image sharpening.
• Topaz Image Lighting — AI-powered lighting adjustment.
• Topaz Image Restore — AI-powered dust and scratch removal.

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": "Normal",
  "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/denoise" \
  -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