Bria Eraser

Bria Eraser

Playground

Bria Eraser delivers SOTA object removal that preserves image quality. Trained on licensed data for safe commercial use; Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Bria Eraser removes selected regions from an image using a mask, then inpaints the missing areas with context-aware detail that matches lighting, perspective, and texture. Trained on licensed data for compliant commercial use across ads, product shots, portraits, and scene cleanup.

✨ Highlights

• Precise control with masks — erase exactly what you mark; keep everything else untouched.
• Context-aware fill — realistic inpainting that blends edges, light, and color.
• Alpha-friendly pipeline — preserve transparency for instant compositing.
• Flexible delivery — sync or async API, URL or BASE64 outputs.

🧩 Parameters (1:1 with the panel)

• image* (required) Source image (URL or upload).

• mask_image* (required) black = keep, white = move

🚀 How to Use

1. Upload/Paste image (required).
2. Upload/Paste mask_image (required). White regions will be removed and inpainted.
3. (Optional) Toggle preserve_alpha if you need transparent output for compositing.
4. Click Run to generate and download your cleaned image.

💰 Pricing

• Per run: $0.04

🧠 Practical Tips

• Mask quality matters: use soft brushes at edges (5–15 px feather) to avoid seams.
• Iterate fast: keep settings, adjust only the mask for rapid alternatives.
• Compositing: with preserve_alpha, drop directly over new backgrounds or graded plates.

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",
  "mask_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
}
JSON
)

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