Bria Ad Delayer API Documentation

Bria Ad Delayer API Documentation

Playground

Bria Ad Delayer splits flat advertisement images into editable image, text, and vector layers, returning a complete structured layer document as JSON for ad editing, localization, redesign, marketing creatives, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Bria Ad Delayer converts a flat advertisement image into editable layer data. It separates the source ad into components such as background, product cutouts, logo cutouts, text, and vector shapes, then returns the complete layer document as JSON.

Why Choose This?

• Ad layer decomposition
  Convert a flat advertisement into structured editable layers.

• Text and vector extraction
  Extract text and vector-style elements as structured layer data.

• Product and logo cutouts
  Separate key visual assets such as products and logos from the original ad.

• Editable text modes
  Use svg to preserve traced letterforms or font for editable text with the nearest matching font.

• JSON workflow output
  Receive the upstream layer document for custom editors, rendering pipelines, and design workflows.

Parameters

Use a flat advertisement image rather than an ordinary photograph.

How to Use

1. Upload an advertisement image — Provide a flat ad image through the uploader or a public URL.
2. Choose text mode optional — Use svg for traced letterforms or font for editable text.
3. Submit — Generate the layer document.
4. Use the JSON output — Read the layer data from json.

Pricing

Pricing is fixed at $0.30 per successful request.

Both svg and font modes use the same fixed price. The number of returned layers does not add separate charges.

Best Use Cases

• Ad creative editing — Break flat ad images into editable components.
• Design reconstruction — Recover layout elements from existing ad creatives.
• Text and logo workflows — Extract text, logos, and vector-like elements for editing.
• Custom rendering pipelines — Use JSON layer data to rebuild ads in your own editor.
• Marketing asset reuse — Separate products, backgrounds, and text for downstream creative work.

Pro Tips

• Use flat advertisement images for better layer separation.
• Use svg when preserving original letter shapes matters.
• Use font when editable text is more important than exact traced appearance.
• Check whether each layer has asset_path before treating it as a downloadable asset.
• Download the layer document and required linked assets promptly.

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",
  "text_mode": "svg"
}
JSON
)

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