Luma Photon Flash API Documentation

Luma Photon Flash API Documentation

Playground

Luma Photon Flash is a Luma text-to-image model that generates images directly from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Generate images at incredible speed and unbeatable value with Luma Photon Flash. At just $0.005 per image, this ultra-fast text-to-image model delivers quality results for rapid prototyping, high-volume generation, and budget-conscious creative work.

Looking for higher quality? Try Luma Photon for enhanced output.

Why It Looks Great

• Unbeatable price: Just $0.005 per image — generate 200 images for $1.
• Flash speed: Optimized for the fastest possible generation.
• Atmospheric scenes: Creates mood-driven, emotionally resonant imagery.
• Prompt Enhancer: Built-in tool to refine your descriptions automatically.
• High-volume ready: Perfect for batch generation and rapid iteration.

Parameters

How to Use

1. Write your prompt — describe the scene, 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

• Rapid Prototyping — Test concepts and ideas at minimal cost.
• High-Volume Generation — Produce large batches affordably.
• Mood Boards — Generate multiple atmospheric images for inspiration.
• Social Media Content — Create visuals for posts and stories quickly.
• Creative Exploration — Experiment freely without budget concerns.

Example Prompts

• “Teen girl journaling in bed by phone flashlight, stuffed animals around her, stickers on the wall, cozy and introspective vibe”
• “Neon-lit ramen shop at night, steam rising, lonely customer at counter”
• “Cat sleeping on a sunny windowsill, dust particles in light, peaceful afternoon”
• “Abandoned amusement park at dusk, nostalgic and slightly eerie atmosphere”
• “Couple sharing headphones on a train, city lights passing by window”

Model Comparison

Pro Tips for Best Results

• Include mood and atmosphere: “cozy”, “introspective”, “nostalgic”, “peaceful”.
• Describe lighting conditions: “phone flashlight”, “neon-lit”, “sunny”.
• Add environmental details for richer scenes.
• At $0.005, generate many variations and pick the best.
• Perfect for exploring ideas before committing to higher-quality generation.
• Flash excels at atmospheric, mood-driven scenes.

Notes

• The most affordable text-to-image option available.
• Flash mode prioritizes speed and cost efficiency.
• Ideal for testing prompts before using premium models.
• Processing is optimized for rapid turnaround.

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 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/luma/photon-flash" \
  -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