Luma Ray 1.6 I2V API Documentation

Luma Ray 1.6 I2V API Documentation

Playground

Luma Ray 1.6 turns images into high-quality videos in multiple sizes with advanced prompt optimization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Transform images into cinematic videos with Luma Ray 1.6 — the latest generation of Luma’s acclaimed video generation model. Known for exceptional camera work, dramatic lighting, and cinematic quality, Ray 1.6 brings still images to life with professional-grade motion and atmosphere.

Why It Looks Great

• Cinematic quality: Creates movie-grade videos with dramatic lighting and composition.
• Advanced camera work: Supports wide-angle shots, close-ups, and dynamic camera movements.
• Atmospheric detail: Renders breath misting, shadows, wind effects, and environmental particles.
• 720p HD output: Sharp, professional-quality video in landscape or portrait.
• Extended duration: Generate up to 10 seconds of video.
• Prompt Enhancer: Built-in tool to refine your motion descriptions.
• Safety Checker: Optional content filtering for appropriate output.

Parameters

How to Use

1. Upload your image — drag and drop or paste a public URL.
2. Write your prompt — describe camera movements, action, and atmosphere in detail.
3. Use Prompt Enhancer (optional) — click to enrich your description.
4. Choose size — select landscape (1280×720) or portrait (720×1280).
5. Set duration — choose 5 or 10 seconds.
6. Run — click the button to generate.
7. Download — preview and save your video.

Pricing

Per 5-second billing based on duration.

Size Options

Best Use Cases

• Cinematic Sequences — Create movie-quality video from still photography.
• Adventure & Outdoor — Animate landscapes, mountains, and nature scenes.
• Documentary Style — Generate atmospheric, story-driven footage.
• Marketing & Ads — Produce premium video content from product images.
• Music Videos — Create visually stunning sequences for audio content.

Example Prompts

• “A man in a hooded jacket climbs a rugged mountain path at dawn, breath misting in the cold air. The rising sun casts long shadows over snow-dusted peaks. Wide-angle shot reveals vast alpine scenery, followed by close-up of his determined face. Wind rustles his jacket.”
• “Slow push-in on subject’s face, dramatic side lighting, subtle expression change”
• “Drone shot ascending over forest canopy, morning mist, golden hour light”
• “Camera orbits around product, studio lighting creating elegant reflections”
• “Waves crashing in slow motion, water droplets catching sunlight, cinematic”

Pro Tips for Best Results

• Luma Ray excels at cinematic language — use film terminology in prompts.
• Describe camera movements: “wide-angle shot”, “close-up”, “push-in”, “drone shot”.
• Include atmospheric details: “breath misting”, “wind rustles”, “shadows”, “mist”.
• Specify lighting: “rising sun”, “golden hour”, “dramatic side lighting”.
• Combine establishing shots with detail shots in your description.
• Ray 1.6 handles environmental effects exceptionally well.

Notes

• Duration options are 5 or 10 seconds.
• If using a URL, ensure it is publicly accessible.
• Enable Safety Checker for content that will be publicly shared.
• Ray 1.6 delivers Luma’s latest video generation capabilities.

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",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "size": "1280*720",
  "duration": 10
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/luma/ray-1.6-i2v" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters