Bria Fibo Relight

Bria Fibo Relight

Playground

Try it on WaveSpeedAI!

Bria Relight modifies the lighting setup (direction and atmosphere) of an image. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Bria Fibo Relight is an AI-powered image relighting model that transforms the lighting conditions of any photo. Choose from a wide variety of lighting styles — from golden sunrise to moonlit nights — and control the light direction for professional-quality results.


Why Choose This?

  • Extensive lighting options Over 10 distinct lighting styles covering all times of day and weather conditions.

  • Directional control Adjust light direction from front, side, bottom, or top-down.

  • Natural results AI understands scene structure for realistic lighting transformations.

  • Simple workflow Upload an image, select lighting style and direction, and get instant results.

  • Versatile applications Perfect for portraits, product photos, and creative projects.


Parameters

ParameterRequiredDescription
imageYesSource image to relight (URL or upload)
light_typeYesLighting style to apply (see options below)
light_directionNoLight direction: front, side, bottom, top-down

Lighting Options

Light TypeDescription
middayBright, overhead sunlight
blue hour lightCool, soft light just before sunrise/after sunset
low-angle sunlightWarm, dramatic light from a low sun angle
sunrise lightGolden, warm morning light
spotlight on subjectFocused dramatic lighting on the subject
overcast lightSoft, diffused cloudy day lighting
soft overcast daylight lightingGentle, even illumination
cloud-filtered lightingSubtle, filtered sunlight through clouds
fog-diffused lightingAtmospheric, misty lighting
moonlight lightingCool, bluish nighttime illumination
starlight nighttimeDim, ambient night lighting

And more.


How to Use

  1. Upload your image — provide the image you want to relight.
  2. Select light type — choose the desired lighting style.
  3. Set light direction (optional) — choose where the light comes from.
  4. Run — submit and download your relit image.

Pricing

OutputCost
Per image$0.04

Best Use Cases

  • Portrait Enhancement — Add golden hour glow or dramatic studio lighting to portraits.
  • Product Photography — Apply consistent, professional lighting to product shots.
  • Social Media Content — Create mood-specific visuals with different lighting styles.
  • Creative Projects — Transform daytime photos to nighttime scenes or vice versa.
  • Photo Correction — Fix poorly lit images with better lighting conditions.

Pro Tips

  • Combine “sunrise light” or “low-angle sunlight” with “side” direction for dramatic portraits.
  • Use “soft overcast daylight lighting” for even, flattering light on faces.
  • “Moonlight lighting” and “starlight nighttime” can transform daytime shots into night scenes.
  • “Spotlight on subject” creates professional studio-style lighting effects.
  • Experiment with different light directions to find the most flattering angle for your subject.

Notes

  • Both image and light_type are required fields.
  • Light direction defaults to a balanced setting if not specified.
  • Ensure uploaded image URLs are publicly accessible.
  • Works best with images that have clear subjects and defined backgrounds.

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",
  "light_type": "midday",
  "light_direction": "front"
}
JSON
)

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

ParameterTypeRequiredDefaultRangeDescription
imagestringYes-The source image to be relighted.
light_typestringYesmiddaymidday, blue hour light, low-angle sunlight, sunrise light, spotlight on subject, overcast light, soft overcast daylight lighting, cloud-filtered lighting, fog-diffused lighting, moonlight lighting, starlight nighttime, soft bokeh lighting, harsh studio lightingThe type of lighting atmosphere to apply.
light_directionstringNofrontfront, side, bottom, top-downThe direction of the light source.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.