Bria Embed Product

Bria Embed Product

Playground

Try it on WaveSpeedAI!

Bria Embed Product seamlessly integrates product images into scene backgrounds with natural lighting and perspective matching. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Bria Embed Product seamlessly embeds product images into background scenes with precise positioning control. Upload a background image and one or more product images with exact placement coordinates — the model intelligently blends products into the scene with natural lighting, shadows, and perspective.


Why Choose This?

  • Precise positioning Specify exact X, Y coordinates and dimensions for pixel-perfect product placement.

  • Multi-product support Embed multiple products into a single scene with individual positioning for each.

  • Intelligent blending Automatically adapts lighting, shadows, and perspective for realistic integration.

  • Simple workflow Define position and size — the model handles the compositing automatically.


Parameters

ParameterRequiredDescription
imageYesBackground image (URL or upload)
productsYesList of products to embed (click ”+ Add Item” to add more)
→ imageYesProduct image (URL or upload)
→ xYesX coordinate for product placement (pixels)
→ yYesY coordinate for product placement (pixels)
→ widthYesProduct width in the output (pixels)
→ heightYesProduct height in the output (pixels)
seedNoRandom seed for reproducibility
enable_sync_modeNoWait for result in response (API only)
enable_base64_outputNoReturn base64 instead of URL (API only)

How to Use

  1. Upload background image — provide the scene where products will be placed.
  2. Add products — for each product:
  • Upload the product image
  • Set X and Y coordinates for placement position
  • Set width and height for product size
  1. Add more products (optional) — click ”+ Add Item” to embed additional products.
  2. Set seed (optional) — for reproducible results.
  3. Run — submit and download your composite image.

Pricing

OutputCost
Per image$0.04

Best Use Cases

  • E-commerce — Place products in lifestyle scenes for catalog and marketing images.
  • Interior Design — Visualize furniture and decor in room settings.
  • Advertising — Create product placement visuals for campaigns.
  • Virtual Staging — Add products to empty spaces for real estate or retail.
  • Product Photography — Composite products into professional backgrounds without physical shoots.

Pro Tips

  • Use transparent PNG product images for best blending results.
  • Coordinate values (x, y) define the top-left corner of the product placement.
  • Match product size (width, height) to the perspective of the background scene.
  • For multiple products, consider their relative positions and overlap.
  • Use a consistent seed to iterate on placement while maintaining the same blending style.

Notes

  • Both image (background) and products are required fields.
  • Each product requires image, x, y, width, and height values.
  • Coordinates are in pixels relative to the background image.
  • Ensure uploaded image URLs are publicly accessible.

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",
  "products": [
    {
      "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
      "x": 1,
      "y": 1,
      "width": 1,
      "height": 1
    }
  ]
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bria/embed-product" \
  -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
imagestringYes-TURL of the image.
productsarray<object>Yes-1 ~ unlimited itemsThis is a controlnet that controls the maximum size of the generated model.
seedintegerNo--Seed for random number generator. Set to -1 to use a random seed.
enable_sync_modebooleanNofalse-If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models.
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.