logo
AI Image
AI Video
Library
Solutions
Community
MCP & CLI
Pricing
  1. Home
  2. AI Models
  3. Luma Ray 3.2 Edit

Luma Ray 3.2 Edit: direct every frame of your AI video

Picsart’s AI Playground now runs Luma Ray 3.2 Edit, the latest video model from Luma Labs built for directed editing rather than prompt-and-regenerate. Reshape footage you already have, place precise keyframes, and carry real performances across takes — all inside your Picsart workflow with cinematic, production-ready output.

Start generating
Woolf
Tofu
Truffle
Silver Scarab
Paris
Nugget
Indigo Sphinx
Sloane
Dumpling
Prescott

What is Luma Ray 3.2 Edit?

Luma Ray 3.2 Edit is the editing-focused release of Luma Labs’ Ray 3.2 video model, announced in June 2026. Instead of regenerating a clip from scratch for every change, it takes a source video and returns a re-imagined version of that same shot — letting you make surgical, directed adjustments. It generates up to 20 seconds at 1080p and is engineered for precision, giving production teams real authority over how a scene moves from start to finish.

Luma Ray 3.2 Edit capabilities

Place up to 16 keyframes inside a single clip to choreograph exact pacing, camera paths, and motion. Enhanced performance tracking carries complex actor performances across takes while tracking the full expressive state of up to eight faces simultaneously, frame by frame. The enhanced reframe tool reshapes a shot after the take — adapt aspect ratios, extend the frame, or replace a background while preserving the original lighting. Native HDR generation and 16-bit EXR export drop cleanly into existing post-production pipelines.

What you can create with Luma Ray 3.2 Edit

Start from a clip you already have and return a re-imagined version of the same shot — make precise, directed changes instead of prompting a brand-new video every time.

Luma Ray 3.2 Edit for directed video editing

How Luma Ray 3.2 Edit works inside Picsart

Picsart integrates Luma Ray 3.2 Edit directly into its AI Playground, so you can direct and refine video without touching the underlying model. It pairs naturally with the AI Video Editor and AI Voice Generator, helping you assemble complete, polished video projects faster.

Why creators choose Luma Ray 3.2 Edit

Creators choose Luma Ray 3.2 Edit when they need control, not luck. Its directed-editing approach means revisions are surgical instead of starting over, performances stay consistent across takes, and pro-grade HDR and 16-bit EXR output slots straight into existing pipelines. Inside Picsart’s AI Video Generator, that production-level command over every frame is available without specialized software or technical setup.



Luma Ray 3.2 Edit FAQ

Luma Ray 3.2 Edit is the editing-focused release of Luma Labs’ Ray 3.2 video model. Rather than regenerating a clip for every change, it takes a source video and returns a directed, re-imagined version of the same shot with frame-level control.

Picsart has integrated Luma Ray 3.2 Edit into its AI Video Generator and AI Playground, so you can direct and refine video content directly in the platform without interacting with the model itself.

Standard models regenerate a whole clip from a prompt. Luma Ray 3.2 Edit is built for directed editing — it edits the footage you already have, supports up to 16 keyframes per clip, and preserves real performances across takes for surgical, repeatable changes.

You can place up to 16 keyframes within a single clip to choreograph pacing, camera paths, and motion, giving you precise authority over how action progresses from the first frame to the last.

Yes. Its enhanced reframe tool lets you adapt aspect ratios for different platforms, extend the frame, or replace a background after the take while preserving the original lighting.

Luma Ray 3.2 Edit generates clips up to 20 seconds long at 1080p, with native HDR generation and 16-bit EXR export designed to drop cleanly into professional post-production pipelines.

Yes. Videos produced through Picsart’s tools powered by Luma Ray 3.2 Edit can be used for marketing, social media, brand content, and other commercial applications, subject to Picsart’s terms of use.


More AI models to use

Luma Ray 2 AI Model

Luma Ray 2

Photorealistic AI video generation with lifelike motion and natural physics.

Runway Aleph 2.0 AI Model

Runway Aleph 2.0

Advanced AI video editing and transformation with strong creative control.

Kling 3.0 AI Model

Kling 3.0

Cinematic AI video generation with advanced motion control and next-level realism.

Picsart AI video Generator

AI Video Generator

Generate custom videos with AI by just writing a short description of your vision.

AI video editor

AI Video Editor

Discover the easiest way to create videos with AI.

AI voiceover generator

AI Voice Generator

Turn your script into natural AI voiceovers in seconds.

Get the free app

Download on the App StoreGET IT ON Google PlayGet it from Microsoft
Pinterest
AICPA SOC

Explore

  • AI Image Generator
  • AI Video Generator
  • AI Playground
  • AI Image Models
  • AI Video Models
  • AI Photo Editor
  • Templates
  • Design Tools

Solutions

  • For Enterprise
  • For Developers
  • For Google Drive
  • For specific Industries
  • Quicktools
  • AI Avatar
  • Pricing

Company

  • Support
  • Careers
  • About us
  • Earn with Picsart
  • Blog
  • Press Center
Terms of UsePrivacy PolicyDo Not SellInternet-Based AdvertisingCommunity GuidelinesDMCASecurity PolicyAccessibility
© 2026 PicsArt, Inc.

Understand video model choices

Learn how to compare video models and direct your output.

Video models

How to choose the right AI video model for your content

4 minIntermediate
How to balance speed and quality in AI video models preview
Video models

How to balance speed and quality in AI video models

4 minIntermediate
How to get the best quality from each video model preview
Video models

How to get the best quality from each video model

5 minAdvanced
How to stay updated with new AI video model features preview
Video models

How to stay updated with new AI video model features

3 minBeginner
See all tutorials
Start editing your videos with Luma Ray 3.2 Edit

Explore more models like Luma Ray 3.2 Edit

Compare Luma Ray 3.2 Edit with other video models for motion, ads, and social clips.

Seedance 2.0New
Next-gen cinematic video with optional audio and reference image. Up to 1080p.Reference inputAudio1080pCinematicSee model
Seedance 2.0 FastNew
Fast cinematic video with audio, reference images, and start/end frame control.Reference inputAudioFast generationCinematicSee model
Seedance 2.0 Video EditNew
Edit video — replace subjects, add or remove objects, restyle scenes with reference images.Video editingReference inputVideo generationSee model
Seedance 2.0 Fast Video EditNew
Fast video edit — modify scenes with reference images.Video editingReference inputFast generationSee model
Sora 2 Pro
Up to 1080p with strong physical realism and optional reference image.Reference input1080pPro qualityCinematicSee model
Sora 2
Naturalistic 720p video with lifelike motion and character detail.CinematicVideo generationSee model
Wan 2.7
Wan 2.7 T2V — up to 15s at 1080p with audio input and prompt enhancement.Text to videoAudio1080pCinematicSee model
Kling V3
Long-form video up to 15s with native audio and start/end frame control.AudioCinematicVideo generationSee model
Kling V2.6
Mature pipeline with audio, adjustable cfg, and standard/pro rendering.AudioPro qualityCinematicSee model
Kling V3 Omni
Flexible generation across creative styles using V3 Omni architecture, with optional 4K output.4KCinematicVideo generationSee model
Kling V3 Turbo
Faster V3 variant — long-form video up to 15s with native audio, start/end frame control, and 720p/1080p output.Audio1080pFast generationCinematicSee model
Kling Video O1
O1-architecture video generation with 5 or 10 second output.CinematicVideo generationSee model
Seedance 2.0New
Next-gen cinematic video with optional audio and reference image. Up to 1080p.Reference inputAudio1080pCinematicSee model
Seedance 2.0 FastNew
Fast cinematic video with audio, reference images, and start/end frame control.Reference inputAudioFast generationCinematicSee model
Seedance 2.0 Video EditNew
Edit video — replace subjects, add or remove objects, restyle scenes with reference images.Video editingReference inputVideo generationSee model
Seedance 2.0 Fast Video EditNew
Fast video edit — modify scenes with reference images.Video editingReference inputFast generationSee model
Sora 2 Pro
Up to 1080p with strong physical realism and optional reference image.Reference input1080pPro qualityCinematicSee model
Sora 2
Naturalistic 720p video with lifelike motion and character detail.CinematicVideo generationSee model
Wan 2.7
Wan 2.7 T2V — up to 15s at 1080p with audio input and prompt enhancement.Text to videoAudio1080pCinematicSee model
Kling V3
Long-form video up to 15s with native audio and start/end frame control.AudioCinematicVideo generationSee model
Kling V2.6
Mature pipeline with audio, adjustable cfg, and standard/pro rendering.AudioPro qualityCinematicSee model
Kling V3 Omni
Flexible generation across creative styles using V3 Omni architecture, with optional 4K output.4KCinematicVideo generationSee model
Kling V3 Turbo
Faster V3 variant — long-form video up to 15s with native audio, start/end frame control, and 720p/1080p output.Audio1080pFast generationCinematicSee model
Kling Video O1
O1-architecture video generation with 5 or 10 second output.CinematicVideo generationSee model
Seedance 2.0New
Next-gen cinematic video with optional audio and reference image. Up to 1080p.Reference inputAudio1080pCinematicSee model
Seedance 2.0 FastNew
Fast cinematic video with audio, reference images, and start/end frame control.Reference inputAudioFast generationCinematicSee model
Seedance 2.0 Video EditNew
Edit video — replace subjects, add or remove objects, restyle scenes with reference images.Video editingReference inputVideo generationSee model
Seedance 2.0 Fast Video EditNew
Fast video edit — modify scenes with reference images.Video editingReference inputFast generationSee model
Sora 2 Pro
Up to 1080p with strong physical realism and optional reference image.Reference input1080pPro qualityCinematicSee model
Sora 2
Naturalistic 720p video with lifelike motion and character detail.CinematicVideo generationSee model
Wan 2.7
Wan 2.7 T2V — up to 15s at 1080p with audio input and prompt enhancement.Text to videoAudio1080pCinematicSee model
Kling V3
Long-form video up to 15s with native audio and start/end frame control.AudioCinematicVideo generationSee model
Kling V2.6
Mature pipeline with audio, adjustable cfg, and standard/pro rendering.AudioPro qualityCinematicSee model
Kling V3 Omni
Flexible generation across creative styles using V3 Omni architecture, with optional 4K output.4KCinematicVideo generationSee model
Kling V3 Turbo
Faster V3 variant — long-form video up to 15s with native audio, start/end frame control, and 720p/1080p output.Audio1080pFast generationCinematicSee model
Kling Video O1
O1-architecture video generation with 5 or 10 second output.CinematicVideo generationSee model
Seedance 2.0New
Next-gen cinematic video with optional audio and reference image. Up to 1080p.Reference inputAudio1080pCinematicSee model
Seedance 2.0 FastNew
Fast cinematic video with audio, reference images, and start/end frame control.Reference inputAudioFast generationCinematicSee model
Seedance 2.0 Video EditNew
Edit video — replace subjects, add or remove objects, restyle scenes with reference images.Video editingReference inputVideo generationSee model
Seedance 2.0 Fast Video EditNew
Fast video edit — modify scenes with reference images.Video editingReference inputFast generationSee model
Sora 2 Pro
Up to 1080p with strong physical realism and optional reference image.Reference input1080pPro qualityCinematicSee model
Sora 2
Naturalistic 720p video with lifelike motion and character detail.CinematicVideo generationSee model
Wan 2.7
Wan 2.7 T2V — up to 15s at 1080p with audio input and prompt enhancement.Text to videoAudio1080pCinematicSee model
Kling V3
Long-form video up to 15s with native audio and start/end frame control.AudioCinematicVideo generationSee model
Kling V2.6
Mature pipeline with audio, adjustable cfg, and standard/pro rendering.AudioPro qualityCinematicSee model
Kling V3 Omni
Flexible generation across creative styles using V3 Omni architecture, with optional 4K output.4KCinematicVideo generationSee model
Kling V3 Turbo
Faster V3 variant — long-form video up to 15s with native audio, start/end frame control, and 720p/1080p output.Audio1080pFast generationCinematicSee model
Kling Video O1
O1-architecture video generation with 5 or 10 second output.CinematicVideo generationSee model
Seedance 2.0New
Next-gen cinematic video with optional audio and reference image. Up to 1080p.Reference inputAudio1080pCinematicSee model
Seedance 2.0 FastNew
Fast cinematic video with audio, reference images, and start/end frame control.Reference inputAudioFast generationCinematicSee model
Seedance 2.0 Video EditNew
Edit video — replace subjects, add or remove objects, restyle scenes with reference images.Video editingReference inputVideo generationSee model
Seedance 2.0 Fast Video EditNew
Fast video edit — modify scenes with reference images.Video editingReference inputFast generationSee model
Sora 2 Pro
Up to 1080p with strong physical realism and optional reference image.Reference input1080pPro qualityCinematicSee model
Sora 2
Naturalistic 720p video with lifelike motion and character detail.CinematicVideo generationSee model
Wan 2.7
Wan 2.7 T2V — up to 15s at 1080p with audio input and prompt enhancement.Text to videoAudio1080pCinematicSee model
Kling V3
Long-form video up to 15s with native audio and start/end frame control.AudioCinematicVideo generationSee model
Kling V2.6
Mature pipeline with audio, adjustable cfg, and standard/pro rendering.AudioPro qualityCinematicSee model
Kling V3 Omni
Flexible generation across creative styles using V3 Omni architecture, with optional 4K output.4KCinematicVideo generationSee model
Kling V3 Turbo
Faster V3 variant — long-form video up to 15s with native audio, start/end frame control, and 720p/1080p output.Audio1080pFast generationCinematicSee model
Kling Video O1
O1-architecture video generation with 5 or 10 second output.CinematicVideo generationSee model
Seedance 2.0New
Next-gen cinematic video with optional audio and reference image. Up to 1080p.Reference inputAudio1080pCinematicSee model
Seedance 2.0 FastNew
Fast cinematic video with audio, reference images, and start/end frame control.Reference inputAudioFast generationCinematicSee model
Seedance 2.0 Video EditNew
Edit video — replace subjects, add or remove objects, restyle scenes with reference images.Video editingReference inputVideo generationSee model
Seedance 2.0 Fast Video EditNew
Fast video edit — modify scenes with reference images.Video editingReference inputFast generationSee model
Sora 2 Pro
Up to 1080p with strong physical realism and optional reference image.Reference input1080pPro qualityCinematicSee model
Sora 2
Naturalistic 720p video with lifelike motion and character detail.CinematicVideo generationSee model
Wan 2.7
Wan 2.7 T2V — up to 15s at 1080p with audio input and prompt enhancement.Text to videoAudio1080pCinematicSee model
Kling V3
Long-form video up to 15s with native audio and start/end frame control.AudioCinematicVideo generationSee model
Kling V2.6
Mature pipeline with audio, adjustable cfg, and standard/pro rendering.AudioPro qualityCinematicSee model
Kling V3 Omni
Flexible generation across creative styles using V3 Omni architecture, with optional 4K output.4KCinematicVideo generationSee model
Kling V3 Turbo
Faster V3 variant — long-form video up to 15s with native audio, start/end frame control, and 720p/1080p output.Audio1080pFast generationCinematicSee model
Kling Video O1
O1-architecture video generation with 5 or 10 second output.CinematicVideo generationSee model