Browse ModelsLumaLuma Ray 2 I2V

Luma Ray 2 I2V

Luma Ray 2 I2V

Playground

Try it on WavespeedAI!

Luma Ray 2 turns images into high-quality videos at multiple output sizes with advanced prompt optimization for precise control. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Luma Ray 2 Image-to-Video

Transform images into premium cinematic videos with Luma Ray 2 — the flagship image-to-video model from Luma Labs. Delivering the highest quality output with exceptional detail, natural motion, and sophisticated camera work, Ray 2 is the choice for professional content creation.

Looking for faster generation? Try Luma Ray 2 Flash I2V for speed-optimized output.

Why It Looks Great

  • Premium quality: Luma’s highest-fidelity image-to-video generation.
  • Exceptional detail: Preserves and enhances fine details from source images.
  • Natural motion: Creates believable, physically accurate movements.
  • Lifestyle mastery: Excels at everyday scenes with warmth and authenticity.
  • 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.

Parameters

ParameterRequiredDescription
imageYesSource image to animate (upload or public URL).
promptYesText description of the motion and atmosphere you want.
sizeNoOutput dimensions: 1280×720 (landscape) or 720×1280 (portrait). Default: 1280×720.
durationNoVideo length: 5 or 10 seconds. Default: 5.

How to Use

  1. Upload your image — drag and drop or paste a public URL.
  2. Write your prompt — describe the motion, ambient details, and atmosphere.
  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.

DurationCalculationCost
5 seconds5 ÷ 5 × $0.40$0.40
10 seconds10 ÷ 5 × $0.40$0.80

Size Options

SizeOrientationBest For
1280×720LandscapeYouTube, presentations, cinematic content
720×1280PortraitTikTok, Instagram Reels, Stories, mobile

Best Use Cases

  • Lifestyle Content — Create warm, authentic scenes of everyday life.
  • Professional Production — Generate client-ready video for commercial use.
  • Ambient Scenes — Animate peaceful, atmospheric environments.
  • Marketing & Advertising — Produce premium video from product photography.
  • Final Deliverables — Maximum quality for projects where output matters.

Example Prompts

  • “Laundry day on a quiet balcony, colorful clothes swaying in the breeze, a woman watering her plants, soft ambient light, distant birds chirping”
  • “Morning coffee ritual, steam rising from cup, gentle hand movements, warm kitchen light”
  • “Cat stretching lazily on a sunlit windowsill, dust particles floating, peaceful afternoon”
  • “Street musician playing guitar, fingers moving on strings, passersby walking, urban atmosphere”
  • “Chef garnishing a dish, precise hand movements, professional kitchen, steam and focus”

Model Comparison

ModelCost (5s)SpeedBest For
Ray 2 I2V$0.40StandardMaximum quality, final deliverables
Ray 2 Flash I2V$0.20FastRapid iteration, dreamy content
Ray 1.6 I2V$0.20StandardCinematic, dramatic content

Pro Tips for Best Results

  • Ray 2 excels at lifestyle and ambient scenes — describe sensory details.
  • Include ambient sounds in prompts: “birds chirping”, “distant traffic”, “wind rustling”.
  • Describe subtle movements: “swaying in the breeze”, “steam rising”, “gentle movements”.
  • Use for final deliverables — test concepts with Ray 2 Flash first.
  • Combine multiple action elements for richer, more dynamic scenes.
  • Perfect for content that needs warmth, authenticity, and natural feeling.

Notes

  • Duration options are 5 or 10 seconds.
  • If using a URL, ensure it is publicly accessible.
  • Ray 2 delivers Luma’s highest quality — ideal for professional work.
  • Premium pricing reflects superior output quality.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/luma/ray-2-i2v" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1280*720",
    "duration": 5
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
imagestringYes-The image for generating the output.
promptstringYes-The positive prompt for the generation.
sizestringNo1280*7201280*720, 720*1280The size of the generated media in pixels (width*height).
durationintegerNo55, 10The duration of the generated media in seconds.

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.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
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, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringArray of URLs to the generated content (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
© 2025 WaveSpeedAI. All rights reserved.