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

Luma Ray 3.2 Reframe: AI video in any aspect ratio

Picsart’s AI Playground now runs Luma Ray 3.2 Reframe, bringing Luma Labs’ latest video model and its Reframe capability into your creative workflow. Reframe, resize, and extend any clip to a new aspect ratio while keeping Ray 3.2’s photorealistic motion, accurate lighting, and cinematic quality — so you can reshape a shot after the take instead of reshooting it.

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

What is Luma Ray 3.2 Reframe?

Luma Ray 3.2 is Luma Labs’ latest AI video model, built for precision with frame-level multi-keyframe control and a native HDR pipeline. Reframe is its standout editing capability: it reshapes an existing shot into a new aspect ratio, intelligently filling the added space and extending the frame while preserving the original lighting and motion. The result is photorealistic video you can adapt to any format without losing cinematic quality.

Luma Ray 3.2 Reframe capabilities

Reframe adapts video across every common aspect ratio — 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, and 9:21 — expanding the frame and generating new content that matches the original scene. Powered by Ray 3.2, it pairs this with frame-level multi-keyframe direction, native HDR with EXR-ready output, and up to 1080p generation. The model keeps reflections, shadows, and materials consistent as it fills new space, so reframed footage stays believable and production-ready.

What you can create with Luma Ray 3.2 Reframe

Turn one clip into vertical 9:16 for TikTok and Reels, 16:9 for YouTube, or 1:1 for the feed — each ratio reframed cleanly with intelligently generated edges.

Luma Ray 3.2 Reframe for multi-platform video

How Luma Ray 3.2 Reframe works inside Picsart

Picsart integrates Luma Ray 3.2 Reframe directly into its AI Playground so you can reframe and resize video without touching the model directly. It works alongside tools like the AI Voice Generator and AI Video Editor, helping you build complete, platform-ready video projects faster.

Why creators choose Luma Ray 3.2 Reframe

Luma Ray 3.2 Reframe lets creators reshape a shot after it’s filmed instead of reshooting. They choose it for clean aspect-ratio changes, intelligent frame extension, and photorealistic fill that preserves the original lighting and physics. Integrated into Picsart’s AI Video Generator, it makes professional, platform-ready reframing accessible without complex setups or specialized equipment.



Luma Ray 3.2 Reframe FAQ

Luma Ray 3.2 Reframe is the Reframe capability of Luma Labs’ Ray 3.2 video model, available in Picsart. It reshapes an existing video into a new aspect ratio, extends the frame, and fills the added space with photorealistic, generated content.

Picsart integrates Luma Ray 3.2 Reframe into its AI Video Generator and AI Playground, so you can reframe, resize, and extend video directly in the platform without interacting with the model itself.

Reframe supports the common formats creators need — 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, and 9:21 — making it easy to adapt one video for social feeds, vertical stories, and widescreen players.

A crop throws away part of the frame. Reframe instead generates new content to extend the frame, intelligently filling added space while preserving the original lighting, motion, and composition for a believable, photorealistic result.

No. Luma Ray 3.2 Reframe works behind the scenes inside Picsart’s AI Video Generator. The tools are built for creators of all levels, with no technical or video editing experience required.

Access depends on the specific tool and subscription plan. Luma Ray 3.2 Reframe is part of the AI models used across Picsart’s platform, with availability varying by feature and tier.

Yes. Videos created through Picsart’s tools powered by Luma Ray 3.2 Reframe 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

Runway Gen 4 AI Model

Runway Gen 4

Cinematic AI video generation with consistent characters and realistic motion.

ai video generation

Veo 3.1

An advanced text-to-video AI model designed to generate high-quality, cinematic videos with realistic motion.

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 voiceover generator

AI Voice Generator

Turn your script into natural AI voiceovers in seconds.

AI video editor

AI Video Editor

Discover the easiest way to create videos with AI.

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 choose an 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
Reframe and generate your video with Luma Ray 3.2 Reframe

Explore more models like Luma Ray 3.2 Reframe

Compare Luma Ray 3.2 Reframe 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