Bria Fibo 2.0 Edit API Documentation

Bria Fibo 2.0 Edit API Documentation

Playground

Bria FIBO 2.0 Image Edit edits one to four reference images with natural-language or structured instructions, supporting masked single-image edits, visual refinements, product visuals, marketing assets, creative content, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Bria FIBO 2.0 Edit transforms existing images with natural-language instructions. Edit a single image, combine multiple references, or use a mask to focus changes on a specific area.

Why Choose This?

• Text-guided editing — Describe changes to subjects, scenes, colors, lighting, and visual style.
• Multi-reference support — Use up to 4 source or reference images in one request.
• Localized editing — Use a black-and-white mask to control where changes are applied.
• Structured instructions — Use structured edit instructions instead of a standard text prompt.
• Flexible framing — Choose from 21 supported aspect ratios or keep the first image’s ratio.
• PNG and JPEG output — Select the output format that fits your workflow.

Parameters

How to Use

1. Upload images — Provide between 1 and 4 source or reference images.
2. Describe the edit — Use prompt or provide a structured_instruction.
3. Add a mask optional — For a single-image edit, use a mask to define the area that should change.
4. Choose framing optional — Select an aspect ratio or keep the first image’s ratio.
5. Choose output format optional — Select png or jpeg.
6. Submit — Generate and retrieve the edited image.

Pricing

$0.04 per request.

Best Use Cases

• Product image editing — Change backgrounds, colors, materials, and presentation.
• Creative compositing — Combine multiple visual references into a new image.
• Localized edits — Modify selected areas while preserving the rest of the image.
• Advertising creatives — Adapt existing assets for campaigns and promotions.
• Scene transformation — Change environments, lighting, styling, or visual direction.
• Multi-reference workflows — Use several images to guide the final composition.

Pro Tips

• Clearly describe what should change and what should remain unchanged.
• Use a mask when the edit needs to stay within a specific area.
• Use multiple references when combining subjects, products, or visual elements.
• Keep large aspect-ratio changes limited when editing a single image.
• Use a fixed seed when comparing prompt or parameter changes.

Notes

• images is required and supports 1–4 images.
• Provide either prompt or structured_instruction, not both.
• mask_image requires exactly one input image.
• The mask must match the source image’s pixel dimensions.
• White mask areas are edited; black areas are preserved.
• Multi-reference edits cannot be combined with a mask.
• If aspect_ratio is omitted, the first image’s ratio is used.
• For single-image edits, the output may retain the source aspect ratio even when a different aspect_ratio is specified. Large aspect-ratio changes may also reduce quality.
• Multi-reference edits support all listed aspect ratios.

Related Models

• Bria FIBO 2.0 Text-to-Image — Generate images from text, reference images, or structured prompts.
• Bria FIBO 2.0 Edit — Edit and combine existing images with text or structured instructions.

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"
  ],
  "aspect_ratio": "1:1",
  "output_format": "png",
  "prompt": "A cinematic ocean wave at sunrise, highly detailed"
}
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-2.0/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

Conditional constraints

• Not allowed: prompt has at most 0 characters or omitted and structured_instruction has at most 0 characters or omitted.
• prompt and structured_instruction cannot be used together.
• Not allowed: images has at least 2 items or omitted and mask_image is provided.

Response Parameters

Result Request Parameters

Result Response Parameters