Bria Product Dimensions API Documentation

Bria Product Dimensions API Documentation

Playground

Bria Product Dimensions creates marketplace-ready product images from product photos and real-world measurements, adding dimension callouts, labels, optional titles, and product facts for e-commerce listings and catalog visuals. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Bria Product Dimensions turns a single product photo and real-world measurements into a clean product dimension image. The model preserves the product, removes the background inside the pipeline, and renders dimension callouts with labels.

Why Choose This?

• Product dimension images Create marketplace-ready dimension visuals from one product photo and measurement values.

• No generative redraw The product is preserved while callout lines and labels are rendered around it.

• Flexible callouts Add height, top width, and bottom width labels with metric or imperial units.

• Style options Choose default, childlike, or elegant callout styling.

• Optional product facts Add a title, weight readout, or capacity readout when needed.

• Standard PNG output Results are returned as PNG image URLs in the standard WaveSpeed prediction response.

Parameters

How to Use

1. Upload product photo - Provide a clear product image.
2. Add dimensions - Enter at least one measurement such as height or bottom width.
3. Choose style - Select the callout visual style.
4. Adjust optional display settings - Add a title, background, weight, or capacity if needed.
5. Submit - Generate the dimension image and retrieve the output URL.

Pricing

Best Use Cases

• Ecommerce product pages - Generate clear dimension images for listings.
• Marketplace assets - Create product visuals for catalogs and online stores.
• Packaging and product content - Show height, width, weight, or capacity in a polished visual.
• Product marketing - Create clean comparison or specification images.
• SKU workflows - Standardize product dimension visuals across many items.

Pro Tips

• Use a clean product photo with the full product visible.
• Use height, width_bottom, and width_top for the clearest callout layout.
• Use dual_parens when you want labels such as 10 in (25.4 cm).
• Keep titles short so they do not crowd the product.
• Use a simple background color for marketplace-style assets.
• Ensure the input image URL is publicly accessible.

Notes

• image, dimensions, and style are required.
• Output format is fixed to PNG.
• The output size defaults to 2200 pixels.

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",
  "dimensions": [],
  "style": "default",
  "units_display": "single",
  "background": "white",
  "title_position": "top_center",
  "weight_unit": "lb",
  "weight_label": "Weight",
  "capacity_unit": "fl_oz",
  "proportional_lines": true
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/bria/product-dimensions" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters