Luma Ray 3.2 Image To Video

Luma Ray 3.2 Image To Video

Playground

Luma Ray 3.2 Image to Video is a fast AI image-to-video generation model that animates a source image into cinematic video guided by a text prompt, with controllable aspect ratio, resolution, duration, and optional reference images. Ready-to-use REST inference API for image animation, cinematic clips, product videos, social media content, advertising creatives, visual storytelling, and professional image-to-video workflows with simple integration, no coldstarts, and affordable pricing.

Features

Luma Ray 3.2 Image-to-Video turns a reference image into a cinematic video clip using a natural-language prompt. It is suitable for animating concept art, character shots, illustrated scenes, marketing visuals, and story-driven still images with controllable duration and resolution.

Why Choose This?

• Image-guided video generation
  Start from a single image and animate it into a short cinematic clip.

• Prompt-based motion control
  Describe subject motion, camera movement, scene evolution, and atmosphere in natural language.

• Multiple resolution tiers
  Choose 540p, 720p, or 1080p depending on your quality and budget needs.

• Simple duration options
  Generate either 5s or 10s clips with predictable pricing.

• Flexible aspect ratio
  Use size presets such as 16:9 for widescreen output.

• Optional reference support
  Add references when you want additional visual guidance for style, subject, or scene consistency.

Parameters

How to Use

1. Upload your image — provide the source image you want to animate.
2. Write your prompt — describe the motion, pacing, mood, and camera behavior you want.
3. Choose size — select the aspect ratio that fits your target format.
4. Choose resolution — use 540p for lower cost, 720p for balanced output, or 1080p for higher quality.
5. Choose duration — select either 5s or 10s.
6. Add references (optional) — include references if you want stronger visual direction.
7. Submit — run the model and download the generated video.

Example Prompt

A cinematic video of a teenage girl crossing a vast desert at sunset, dragging a small cart filled with scrap metal. She discovers a damaged robot half-buried in the sand. At first she points a tool at it cautiously, but the robot weakly raises one hand and offers her a tiny glowing flower made of metal. She slowly lowers her guard and smiles. The camera starts with a wide desert landscape, then moves into a gentle close-up of the girl and the robot. Golden sunset, blowing sand, emotional sci-fi adventure, warm and hopeful tone.

Pricing

Pricing depends on duration and resolution.

Billing Rules

• Base price is $0.50 for a 5s video at 540p
• 10s costs 2× the 5s rate
• 720p costs 2× the 540p rate
• 1080p costs 4× the 540p rate
• Pricing depends only on duration and resolution

Best Use Cases

• Still-image animation — Turn a single image into a short motion clip.
• Character shots — Animate portraits, concept characters, or key visual frames.
• Story visualization — Bring illustrated scenes or concept art to life.
• Social media content — Create short eye-catching videos from static assets.
• Creative prototyping — Quickly test motion direction and camera ideas from one image.

Pro Tips

• Use a clear, high-quality input image for better motion quality.
• Be specific about motion, camera movement, and emotional tone in your prompt.
• Start with 5s for faster iteration, then move to 10s when you want more scene development.
• Use 540p or 720p for testing and 1080p for higher-end output.
• Keep prompts focused on animation, motion, and scene progression rather than repeating static visual details already shown in the image.

Notes

• image and prompt are required.
• duration currently supports 5s and 10s.
• Pricing depends only on the selected duration and resolution.
• Reference input is optional.

Related Models

• Luma Ray 3.2 Text-to-Video — Generate videos directly from text prompts.
• Luma video workflows — Explore other video generation and editing models on WaveSpeed.

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",
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "16:9",
  "resolution": "540p",
  "duration": "5s"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/luma/ray-3.2/image-to-video" \
  -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