Bria Fibo Restore API Documentation

Bria Fibo Restore API Documentation

Playground

Bria Restore renews old photos by removing noise, scratches, and blur. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Bria Fibo Restore is an AI-powered photo restoration model that repairs and enhances old or damaged photographs. Upload your vintage photo and the model automatically fixes scratches, fading, noise, and other degradation — bringing old memories back to life.

Why Choose This?

• Automatic restoration Intelligently detects and repairs common photo damage without manual intervention.

• Scratch and damage repair Removes scratches, tears, creases, and other physical damage marks.

• Noise and grain reduction Cleans up film grain and digital noise while preserving detail.

• Fade correction Restores color vibrancy and contrast lost to age.

• Simple one-click workflow Just upload an image — no complex parameters needed.

Parameters

How to Use

1. Upload your image — provide the old or damaged photo you want to restore.
2. Run — submit and download your restored image.

Pricing

Best Use Cases

• Family Photo Restoration — Repair old family portraits and vintage snapshots.
• Historical Archives — Restore aged documents and historical photographs.
• Professional Restoration — Quickly process damaged photos for clients.
• Memory Preservation — Digitize and enhance old photo albums.
• Print Preparation — Clean up vintage photos for reprinting or framing.

Pro Tips

• Scan old photos at high resolution for best restoration results.
• Works well on both black-and-white and color vintage photos.
• Combine with Bria Fibo Colorize to add color to restored B&W photos.
• For severely damaged photos, results may vary — multiple processing may help.
• Ensure uploaded image URLs are publicly accessible.

Notes

• Only image is required — the model automatically detects and repairs damage.
• Works best on photos with typical age-related degradation (scratches, fading, noise).
• Extreme damage or missing portions may not be fully recoverable.

Related Models

• Bria Fibo Colorize — Add color to restored B&W photos.
• Bria Fibo Relight — Adjust lighting conditions on images.
• Bria Fibo Reseason — Change the season or weather of images.
• Bria Fibo Image Blend — Blend multiple images together.

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"
}
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/fibo/restore" \
  -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

Response Parameters

Result Request Parameters

Result Response Parameters