Image Watermark Remover API Documentation

Image Watermark Remover API Documentation

Playground

Intelligently detects and removes text and logo watermarks while preserving texture and background for natural, artifact-free images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

The AI Image Watermark Remover is a precision inpainting model designed to remove text, logos, or unwanted marks from your photos and artworks. Powered by WaveSpeedAI’s next-generation visual reconstruction engine, it restores the occluded background with natural detail and color continuity.

⚙️ Key Features

• Smart Watermark Detection Automatically identifies watermarks, text overlays, or logos across images.

• High-Fidelity Restoration Reconstructs occluded areas with realistic background textures and tones.

• Multi-Zone Editing Support Remove multiple regions in a single pass — perfect for batch cleanup.

• Preserve Artistic Integrity Retains lighting, color, and composition to ensure natural visual balance.

• Flexible Output Formats Export results in JPEG, PNG, or WEBP format.

• Fast Processing Optimized for WaveSpeedAI inference clusters, ensuring near-instant cleanup even for high-resolution images.

💡 Recommended Use Cases

• Removing watermarks or timestamps from photos
• Cleaning logos or marks from AI-generated images
• Restoring old artworks or scanned prints
• Preparing marketing or e-commerce visuals for reuse

💰 Pricing

Each run costs $0.012 — pay only for what you use.

📝 Notes

• Avoid uploading images that contain copyrighted logos unless you own the rights.
• Works best when the watermark area is not excessively large or opaque.
• For highly complex overlays, try the Ultimate Image Eraser for enhanced reconstruction quality.

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",
  "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/wavespeed-ai/image-watermark-remover" \
  -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