Bria Fibo

Bria Fibo

Playground

FIBO is an open-source JSON-native text-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’s Fibo is a fast, SOTA Open source model trained on licensed data. It supports prompt + negative prompt, structured prompts (for consistent layouts/brand objects), controllable aspect ratios, and seed reproducibility—great for ads, social posts, product shots, and concept art.

✨ Highlights

• Strong composition control — prompt + negative prompt + structured prompt.
• Production-ready outputs — crisp details and balanced lighting across common aspect ratios.
• Deterministic renders — set a seed to reproduce the same image; change the seed to explore variants.
• Creator workflow fit — square 1:1 by default; export-friendly for design tools.

🧩 Parameters

• prompt* (string, required) Your text description of the scene/subject, camera, lighting, style, colors, etc.

• aspect_ratio (dropdown) Output canvas proportion. The panel shows 1:1; common options typically include 1:1, 16:9, 9:16, 4:5, 3:2 (availability may vary).

• negative_prompt (string, optional) What to avoid (e.g., “blurry, extra fingers, watermark, text artifacts, distorted face”).

• structured_prompt (string/JSON, optional) For schema-style guidance such as object lists, layout slots, or color constraints. Example idea: {“subject”:“red running shoes”,“background”:“studio white”,“key_light”:“soft”}

• seed (integer, optional) Fixes randomness. Same prompt + params + seed → same image. Leave blank to randomize.

> Fields marked with * are required.

🚀 How to Use

1. Write the prompt (required). Be clear about subject, setting, lighting, and style. Example: “A cozy rooftop garden in Paris at night, warm string lights, shallow depth of field, cinematic glow.”

2. Choose aspect_ratio.

• Social square → 1:1
• Landscape/YouTube banner → 16:9
• Portrait/Reels → 9:16

3. (Optional) Add a negative_prompt. Steer the output away from unwanted traits. Example: “low-res, blurry, text, watermark, extra fingers, distorted proportions.”

4. (Optional) Use structured_prompt. Provide a compact schema to lock composition or brand elements. Great for repeatable shots.

5. (Optional) Set seed. Use a fixed number to reproduce a result; refresh to explore variants.

6. Run to generate your image. If you like the composition but want alternatives, keep all settings the same and only change the seed.

Price

• $0.04 per image.

Notes

• Omit seed to randomize.
• structured_prompt may be sent as a JSON string or object depending on your client—keep it compact and valid.

🧠 Prompting Tips

• Pair a clear subject with lighting and camera cues: “soft studio key light,” “35mm lens,” “golden hour backlight.”
• Use negative prompts early to block common artifacts (e.g., “text, watermark, extra limbs”).
• For consistent campaigns, keep a fixed seed + structured prompt and only tweak small attributes (color, pose, prop).

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'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "seed": -1
}
JSON
)

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