Bria Fibo Edit API Documentation

Bria Fibo Edit API Documentation

Playground

FIBO is an open-source JSON-native image-to-image model that maps intent to structured controls for precise enterprise image generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Bria FIBO Edit is a powerful image editing model that transforms images based on text prompts. Upload your images, describe the changes you want, and optionally provide a mask to target specific areas — the model applies intelligent edits while preserving the overall composition and quality.

Why Choose This?

• Text-guided editing Describe edits in natural language — change objects, modify styles, transform products, and more.

• Mask support Optionally provide a mask image to target specific areas for precise, localized edits.

• Multi-image input Upload multiple reference images for context-aware editing.

• Negative prompt support Specify what to avoid in the output for better control over results.

• Structured prompts Advanced prompt formatting for complex editing instructions.

Parameters

How to Use

1. Write your prompt — describe the edit you want (e.g., “Product becomes perfume”, “Change background to beach”).
2. Upload images — add source images using ”+ Add Item” button.
3. Add mask (optional) — upload a mask to target specific areas.
4. Add negative prompt (optional) — specify what to avoid.
5. Set seed — use -1 for random, or specify a number for reproducibility.
6. Run — submit and download the edited image.

Best Use Cases

• Product Transformation — Change product types while maintaining composition.
• Object Replacement — Swap objects in images with text instructions.
• Style Editing — Modify visual styles, colors, or aesthetics.
• Background Changes — Transform backgrounds while preserving subjects.
• Creative Retouching — Apply artistic edits with natural language.

Pro Tips

• Be specific in your prompt — clearly describe what should change.
• Use mask images for precise control over which areas to edit.
• Use negative prompts to avoid unwanted elements in the output.
• Start with simple edits to understand how the model interprets prompts.
• Use the same seed to compare different prompts on the same image.

Notes

• Multiple images can be uploaded for context-aware editing.
• Mask image should be black and white — white areas will be edited.
• For best results, use high-quality source images.

Related Models

• Qwen Image Edit 2511 — Precise image editing with bilingual text support.
• Qwen Image Edit Plus — Enhanced editing with dual-mode and text editing.

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'
{
  "images": [
    "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/edit" \
  -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