Suggested searches

GPT Image Introduction GPT Image Free Guides GPT Image Developer Docs Midjourney Introduction Midjourney Free Guides Midjourney Developer Docs Google Nano Banana Introduction Google Nano Banana Free Guides Google Nano Banana Developer Docs Adobe Firefly Image Introduction Adobe Firefly Image Free Guides Adobe Firefly Image Developer Docs FLUX Introduction FLUX Free Guides FLUX Developer Docs Ideogram Introduction Ideogram Free Guides Ideogram Developer Docs Recraft Introduction Recraft Free Guides Recraft Developer Docs Stable Diffusion Introduction ByteDance Seedream Introduction Grok Imagine Image Introduction Google Veo Introduction Google Veo Free Guides Google Veo Developer Docs Runway Introduction Kling AI Introduction ByteDance Seedance Introduction ByteDance Seedance Free Guides ByteDance Seedance Developer Docs Luma AI Introduction Adobe Firefly Video Introduction Adobe Firefly Video Free Guides Adobe Firefly Video Developer Docs Hailuo AI Introduction PixVerse Introduction PixVerse Free Guides PixVerse Developer Docs Pika Introduction Pika Free Guides Pika Developer Docs Alibaba Wan Introduction LTX Video Introduction Grok Imagine Video Introduction Google Gemini Introduction Google Gemini Free Guides Google Gemini Developer Docs OpenAI GPT Introduction Claude Fable Introduction Claude Fable Free Guides Claude Fable Developer Docs DeepSeek Introduction Qwen Introduction Llama Introduction Codex Introduction Codex Free Guides Codex Developer Docs Cursor Introduction Cursor Free Guides Cursor Developer Docs OpenClaw Introduction OpenClaw Free Guides OpenClaw Developer Docs Perplexity Introduction ElevenLabs Introduction Suno Introduction Manus Introduction Claude vs ChatGPT: Compare Them Without Borrowed Numbers Claude vs Gemini: Comparing Two Assistants Honestly Is Adobe Firefly Free? The Free Membership, the Credits and the First Year Adobe Firefly Pricing: Plans, Generative Credits and the Cost of One Image Adobe Firefly Video Cost: Credits per Second and per Clip Is Adobe Firefly Video Free? Where the Free Plan Stops FLUX.2 Prompt Guide: The Structure Black Forest Labs Documents FLUX.2 vs Nano Banana Pro: What Each Vendor Actually Publishes Ideogram 4.0 Prompt Guide: The Documented Structure and How Text Renders Ideogram Pricing: Plans, Credits and the Free Limits Midjourney Prompt Guide: Structure, Elements and Edit Instructions Midjourney Pricing: Four Plans, GPU Hours and What a Job Costs Nano Banana Pro Pricing: What Google Publishes and What It Does Not Nano Banana Pro vs Midjourney: Which One Fits Your Workflow Pika Credits: What One Pika 2.5 Video Costs Is Pika Free? What the $0 Plan Actually Includes What PixVerse Credits Cost, and Which Ledger You Are Paying Is PixVerse Free? Two Free Tiers, and What Each One Costs You Recraft V4.1: The Eight Variants and Which to Pick Recraft Pricing and the Free Plan: What the Vendor Publishes Seedance Official Website: Which Entrances Are First-Party Seedance 2.5 vs 2.0: The Parameters ByteDance Publishes Veo 3.1 vs Sora 2: What Each Vendor Still Confirms Veo 3.1 vs Kling 3.0: What Each Vendor Publishes Is Claude AI Free? What the $0 Plan Actually Gives You Claude Pricing Plans: Pro vs Max 5x vs Max 20x How to Use Adobe Firefly (Adobe Firefly Image 5) Adobe Firefly API: Credentials, Endpoints and the Image5 Schema How to Use Adobe Firefly Video Adobe Firefly Video API: /v3/videos/generate Explained Designing UI Mockups and App Screens with GPT Image 2.5 Sticker Packs and Transparent Emoji with GPT Image 2.5 Nano Banana Pro Prompt Guide: The Official Frameworks Is Nano Banana Pro Free? What Google Actually Confirms How to Use Pika 2.5 Pika API: the official developer site, billing and endpoints How to Use PixVerse PixVerse API: Platform, Endpoints and Credits How to Use ByteDance Seedance 2.5 Seedance API: The Real Endpoint, Model ID and Fields Veo 3.1 Prompt Guide: The Seven Elements Google Names Veo 3.1 Price and Free Access: The Official Numbers How to Use Claude AI Claude API: Getting Started How to Use FLUX AI: A FLUX.2 Getting-Started Guide FLUX.2 API: Getting Started with Black Forest Labs GPT Image 2.5 vs DALL·E 3 Making Infographics and Diagrams with GPT Image 2.5 How to Use Ideogram Ideogram API: Access, Endpoints and Text Rendering How to Use Midjourney V8.2 Midjourney API: What Exists and What Does Not How to Use Nano Banana Pro Nano Banana Pro API: Getting Started How to Use Recraft Recraft API: Access, Endpoints and Style Consistency How to Use Veo 3.1 Veo 3.1 API Pricing and Vertex AI Access GPT Image 2.5 Prompt Sharing GPT Image 2.5 vs Nano Banana 2 GPT Image 2.5 vs Seedream 5.0 Pro GPT Image 2.5 vs FLUX 2 GPT Image 2.5 vs Ideogram Is GPT Image 2.5 Free GPT Image 2.5 Sketch GPT Image 2.5 Templates GPT Image 2.5 Comment Editing GPT Image 2.5 Character Consistency GPT Image 2.5 Combine Images GPT Image 2.5 Text Rendering What Is GPT Image 2.5 GPT Image 2.5 API Overview Codex vs. ChatGPT: Which Should You Use? Codex app, CLI, IDE, or cloud: how to choose the right surface Your First Low-Risk Coding Task with Codex: A Safe Walkthrough What Is Cursor? Its AI Coding Workflow Explained Cursor vs. VS Code: Which Editor Fits Your Workflow? Cursor Features Explained: Agent, Tab, Context, and More What Is Gemini? Apps, Models, AI Studio, and API Explained Gemini Apps vs. Gemini API: How to Choose the Right Tool for the Job What Can Gemini Do? A Practical Capability Guide OpenClaw Foundation Explained: Governance and Independence OpenClaw Skill Workshop Guide: Review Reusable Workflows OpenClaw Skill Cards: Read ClawHub Security Scans OpenClaw 2.0 Guide: New Features and Upgrade Checks OpenClaw LTS Guide: Choosing extended-stable or stable Install OpenClaw: Desktop, Script, npm, and Source Options OpenClaw Node.js Setup: Versions, Installation, and PATH How to Write Better Codex Prompts: A Practical Framework How to Review Codex Code Changes Before You Commit Cursor Beginner Tutorial: From Install to First Reviewed Edit Cursor Rules Tutorial: Project Rules, User Rules, and AGENTS.md Install Cursor on Windows and Configure a Chinese Interface Cursor MCP Tutorial: Configure, Verify, and Secure MCP Servers Gemini Prompt Guide: Better Instructions and Templates Gemini API Quickstart: Key, Python SDK and First Call Gemini Web App Guide: Login, Files, Chats and Privacy Gemini API Key Security: Storage, Restrictions and Rotation What Is Codex? Capabilities, Limits, and Ways to Use It Codex Beginner Tutorial: Complete Your First Safe Task Install Codex CLI: Sign In and Run Your First Safe Task Codex AGENTS.md Guide: Layered Rules and Validation Codex CLI Commands: Sessions, Review, and Automation How to Use Gemini: Web, Android & iPhone Setup Gemini Features Guide: Chat, Files, Images & Live How to Chat with Gemini: Prompts, Follow-Ups & Live Gemini AI Image Generator Guide: Prompts & Editing Gemini vs GPT-4: Features, Limits & Which to Use Gemini AI Assistant Guide: Mobile, Apps & Privacy Gemini Prompt Engineering Guide: Patterns & Examples Gemini Chat API Guide: Multi-Turn Prompts in Python Gemini System Instructions: API Guide & Examples Gemini Context Caching Guide: Cost, Latency & API
AI Tool Blog Luma Ray3.2 learning hub

Finish every cut with Ray3.2.

Luma Ray3.2 is Luma’s current video model, pitched at production pipelines rather than one-off clips: 1080p in every mode, up to 16 keyframes inside a single clip, and native 16-bit HDR output that is meant to drop into a colour pipeline you already run.

Capabilities and specifications on this page come from Luma’s model page, its launch announcement and its API documentation. Credits and plan prices are set by the vendor and change without notice.

Official examples

What Luma Ray3.2 renders

These frames come from Luma’s own Ray3.2 page. The page presents them beside eight named workflows — motion transfer, relighting, product swap and so on — but it does not label each frame, so the captions below describe only what is visible and make no claim about which workflow produced it.

Official Luma Ray3.2 example of a roller coaster and park buildings caught in motion
Motion at speed: a roller coaster and the park buildings around it, caught mid-movement with the colours intact.
Official Luma Ray3.2 example of a bearded man in a plaid shirt at a scrapyard
Documentary realism: a bearded man in a plaid shirt at a scrapyard, the kind of unstyled location portrait an advertising spot would otherwise need a crew for.
Official Luma Ray3.2 example of a lone hiker in orange on a green mountain ridge
Scale in landscape: a lone hiker in orange on a green mountain ridge, with the figure small enough to read as distance rather than as a subject.
Official Luma Ray3.2 example of a woman writing at a desk in window light
Interior light: a woman writing at a desk in a brightly lit room, the register that a relighting workflow is judged on.
Official Luma Ray3.2 example of a hand pouring into a glass of iced water by the sea
Tabletop product work: a hand pouring into a glass of iced water against a sea horizon, the sort of shot a brand would normally schedule a shoot for.
Official Luma Ray3.2 example of a woman holding an orange bottle against a blue sky
Campaign framing: a woman holding a bright orange bottle against a blue sky, the look Luma sells as market-specific campaign variation.

Example images belong to Luma and are reproduced with credit: Luma Ray3.2 model page

What it is

Ray3.2 as Luma describes it

Luma positions Ray3.2 less as a prompt box and more as a model that plugs into post. Four claims carry that positioning.

01

1080p in every mode

Luma states 1080p outputs across every mode rather than reserving it for the flagship one, so resolution is not the lever you trade away for speed.

02

Direction inside the clip

Multi-Keyframe places up to 16 keyframes in a single clip, which is how you decide what changes and what holds instead of re-rolling the whole shot.

03

Editing footage you already have

Modify Video V2 reshapes existing footage — Luma’s own wording is to swap the wall, the world, the wardrobe — for up to 20 seconds, with the lighting held and the performance preserved.

04

Built for the finishing room

Native 16-bit HDR is generated by the model, and 16-bit EXR frames come out in ACES2065-1 (AP0) — the format a colourist or compositor expects to load.

Documented credit costs

What a Ray3.2 task costs in credits

Luma publishes its own credit table, so these are vendor figures rather than estimates. They are credits, not currency: what a credit costs depends on the plan. The 1080p column is the one most production work lands in.

Task 1080p credits Notes
Text to video / image to video, 5 s 400 Base generation at full resolution
Text to video / image to video, 10 s 1,200 Three times the 5-second cost, not double
Video to video, 5 s 720 Priced above straight generation
Video to video, 10 s 1,440 Twice the 5-second video-to-video cost
Reframe, per second 120 Re-cuts a finished clip into another aspect ratio

Luma bills HDR output at twice the standard rate and HDR with EXR export at three times, per its own output-format table.

Named workflows

The eight workflows Luma publishes

Luma sells Ray3.2 as a set of named workflows rather than one prompt box. These are the official names and, in paraphrase, the official one-line descriptions.

01

Motion Transfer

Moves movement and dynamics across characters, objects and materials, so the choreography survives the swap of who performs it.

02

Camera Motion Transfer

Moves a cinematic camera move across scenes, worlds and styles.

03

Character Transformation

Turns people into entirely new characters while keeping the performance.

04

Visual Effects

Creates cinematic effects and transformations while the scene stays consistent.

05

Environment Change

Changes the environment to any setting, season or world.

06

Relighting

Changes the lighting to match an environment, a time of day or a creative direction.

07

Product Swap

Adapts a product across campaigns without a reshoot or manual editing.

08

Global Campaigns

Produces market-specific campaign variations without a reshoot.

Documented specifications

What Luma publishes about Ray3.2

Only facts Luma states on its own pages appear here. Where the vendor publishes nothing, the row says so rather than quoting a reseller.

Developer
Luma AI
Current model
Ray3.2
Output resolution
1080p across every mode
Clip length
Up to 20 seconds for Modify Video V2; the launch announcement describes 10-second generations, so the two pages read differently
Keyframes
Up to 16 in a single clip (Multi-Keyframe)
Aspect ratios
Reframe handles every aspect ratio
Colour
Native 16-bit HDR, generated by the model
Export
16-bit EXR frames, ACES2065-1 (AP0)
Audio
Not published: no audio capability or audio price appears in Luma’s specification or pricing tables
Draft tiers
360p and 540p sit below 720p for cheaper iteration
Weights
Not published; hosted only
How to use it

Documented access channels

Luma publishes one first-party page, one programmatic route and one partner route. The weights are not downloadable, so all of them are hosted.

Ray3.2 model page

Luma’s own page for the model, with the workflow descriptions and the full credit table.

Open

Luma Agents API

Luma documents video generation through its Agents API, which is the programmatic entry point.

Open

Launch announcement

The newsroom post introducing Ray3.2 and describing what changed from earlier Ray models.

Open

Partner platforms

Luma names partner platforms on its model page. The model is the same; the commercial terms are the partner’s.

FAQ

Luma Ray3.2 questions people search for

What is Luma Ray3.2?

Luma’s current video model, built around production workflows. Luma states 1080p output in every mode, up to 16 keyframes per clip and native 16-bit HDR.

Is Luma Ray3.2 free?

Luma prices Ray3.2 in credits rather than free generations. The credit cost per task is published; what a credit costs depends on the plan you are on.

How long can a Luma Ray3.2 clip be?

Luma’s model page says up to 20 seconds for Modify Video V2, while the launch announcement describes 10-second generations. The two official pages do not read the same, so treat 20 seconds as the ceiling the model page claims.

Does Luma Ray3.2 generate audio?

Luma publishes no audio capability and no audio price for Ray3.2 — neither the specification list nor the credit table carries an audio line. Treat sound as something you add afterwards.

What resolution does Luma Ray3.2 output?

1080p across every mode, with 360p and 540p draft tiers below it for cheaper iteration.

Can I run Luma Ray3.2 locally?

No. The weights are not published, so Ray3.2 is reachable through Luma’s own products and its Agents API, or through partner platforms.

What can Luma Ray3.2 edit?

Luma names eight workflows: motion transfer, camera motion transfer, character transformation, visual effects, environment change, relighting, product swap and global campaigns.