Bria Expand

Bria Expand

Playground

Try it on WaveSpeedAI!

Bria Expand grows images beyond borders by generating new pixels to fit any aspect ratio; trained on licensed data for commercial use. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Bria Expand extends an image beyond its original borders with intelligent outpainting. Keep the original content intact while the model hallucinates plausible surroundings, matching lighting, perspective, and texture. Built on licensed training data for safe commercial use in banners, thumbnails, hero images, and cinematic wides.


✨ Highlights

  • Context-aware outpainting: expands left/right/top/bottom while preserving subject integrity.
  • Layout control: choose a target aspect ratio (e.g., 16:9, 9:16) to fit ads, covers, or reels.
  • Production-ready pipeline: synchronous result retrieval or async polling; URL or BASE64 output.
  • Compositional consistency: lighting and perspective blend naturally with the original image.

🧩 Parameters (1:1 with the panel)

  • image* (required) Input image (URL or upload). This is preserved; the model generates the new perimeter around it.

  • aspect_ratio* (dropdown, required) Target canvas proportion after expansion (e.g., 16:9, 9:16, 1:1, 4:5, etc.). The model expands to reach this ratio.


🚀 How to Use (panel flow)

  1. Upload/Paste image (required). Start with a clean, reasonably high-res shot.
  2. Select aspect_ratio to match your target placement (e.g., 16:9 for banners, 9:16 for shorts).
  3. Click Run to generate the expanded canvas and download.

Tip: If a side looks too “invented,” try a slightly different ratio (e.g., from 16:9 to 3:2) or crop the original to nudge composition before expanding again.


💰 Pricing

  • Per run: $0.04

🧠 Workflow Tips

  • Plan the frame: choose the final placement (web hero, mobile cover) first, then set aspect_ratio.
  • Edge cleanliness: if seams appear, run a mild feather/refine-edge pass or a quick inpainting touch on the borders.
  • Brand safety: avoid generating around logos/trademarks that must remain untouched—mask and lock them in post if needed.
  • Batch resizing: standardize on a few aspect ratios (e.g., 1:1, 4:5, 16:9, 9:16) to streamline campaigns.

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",
  "aspect_ratio": "1:1"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bria/expand" \
  -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-The URL of the image to erase.
aspect_ratiostringYes1:11:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9Aspect ratio for expansion.Input Image Area: Ensure that the ratio of the input image foreground or main subject to the canvas area is greater than 15% to achieve optimal results.
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.