Luma Photon

Luma Photon

Playground

Luma Photon is a text-to-image model that converts text prompts into images for prompt-based visual generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Generate beautiful, atmospheric images with Luma Photon — Luma’s flagship text-to-image model. Known for stunning lighting, natural compositions, and emotionally resonant scenes, Photon delivers professional-quality results at an affordable price.

Looking for faster generation? Try Luma Photon Flash for speed-optimized output at the lowest cost.

Why It Looks Great

• Stunning lighting: Exceptional at natural light, golden hour, and atmospheric glows.
• Emotional resonance: Creates scenes with mood, warmth, and authentic feeling.
• Natural compositions: Produces balanced, visually pleasing layouts.
• Environmental detail: Rich textures like flour dust, steam, and ambient particles.
• Prompt Enhancer: Built-in tool to refine your descriptions automatically.
• Affordable quality: Professional results at just $0.015 per image.

Parameters

How to Use

1. Write your prompt — describe the scene, lighting, mood, and atmosphere.
2. Use Prompt Enhancer (optional) — click to automatically enrich your description.
3. Run — click the button to generate.
4. Download — preview and save your image.

Pricing

Flat rate per image.

Best Use Cases

• Lifestyle Photography — Generate authentic, warm scenes of everyday moments.
• Food & Bakery — Create appetizing culinary and artisan imagery.
• Interior Scenes — Produce cozy, inviting indoor environments.
• Portrait & Character — Generate natural-looking people in context.
• Marketing Content — Create professional visuals for brands and campaigns.

Example Prompts

• “Baker arranging bread on wooden shelves in a rustic bakery, flour dust in the air, morning glow from the window”
• “Barista pouring latte art, steam rising, warm cafe lighting, artisan coffee shop”
• “Grandmother reading to grandchild on a cozy couch, soft lamp light, warm evening”
• “Florist arranging bouquet in sunlit shop, petals scattered on counter, peaceful morning”
• “Chef plating dish in restaurant kitchen, focused expression, professional environment”

Model Comparison

Pro Tips for Best Results

• Photon excels at natural lighting — describe light sources and quality.
• Include atmospheric particles: “flour dust”, “steam rising”, “dust motes”.
• Specify time of day: “morning glow”, “golden hour”, “soft evening light”.
• Describe textures and materials: “wooden shelves”, “rustic”, “artisan”.
• Add emotional context: “cozy”, “peaceful”, “focused”, “warm”.
• Luma models are known for photorealistic, emotionally authentic scenes.

Notes

• Photon delivers Luma’s best quality for text-to-image generation.
• Processing is fast with professional-grade output.
• Ideal for final deliverables and client-facing work.
• For rapid iteration at lowest cost, use Photon Flash.

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"
}
JSON
)

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