Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Most reframe tools crop, downsize, or hallucinate. Introducing the LTX Reframe API. Expand any video to a new aspect ratio. The original frame stays untouched. The model generates only what’s beyond the edges. • Full source length, up to 60s • Native 1080p • 16:9, 9:16, 1:1, 4:5 •... show more

LTX.io

41,051 subscribers

1,861,855 views • 3 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

16 Comments

𝚛𝚊𝚛𝚎𝚜𝚝 𝚙𝚒𝚗𝚔𝚒𝚎𝚖𝚊𝚗3 months ago

thanks, LTX. very cool!

LTX.io3 months ago

Try it today:

awesome_visuals3 months ago

wow! v cool

sabir hussain3 months ago

Keeping the original frame intact is a big advantage.

Zora Vale AI3 months ago

This is a smart approach to video reframing—keeping the original intact while expanding beyond the frame is much more useful than simple cropping.

LTX.io3 months ago

Exactly!

Markandey Sharma3 months ago

This could make repurposing long-form content much easier.

IamAlam3 months ago

i will try it

A.W.E.S.O.M.-O 40003 months ago

Smart video expansion unlocks effortless content for every social platform format.

LTX.io3 months ago

😎

AI Mastery Guide3 months ago

Keeping the original frame untouched is the smart move here.

TotalWorld3 months ago

most miniapps should stick to native video if possible instead of refraeming. 60s is too long for a mobile video ad though, even at 1080p. Sounds like a fun hack though!

Max12763 months ago

Amazing 👏

Arsalan3 months ago

Love that it expands the scene instead of changing it

Adam Iverson3 months ago

Really needed this, thank you!

PC enthusiast3 months ago

when new ltx model?

Related Videos

Introducing fal Reframe. Change any video's aspect ratio without cropping or reshooting. Powered by H3 Max, Reframe extends your scene beyond the original frame while preserving the footage, timing, and audio. Go from vertical to widescreen, 9:16 to 1:1, and more.

Introducing fal Reframe. Change any video's aspect ratio without cropping or reshooting. Powered by H3 Max, Reframe extends your scene beyond the original frame while preserving the footage, timing, and audio. Go from vertical to widescreen, 9:16 to 1:1, and more.

fal

18,564 views • 20 days ago

Introducing LTX-2.3 Our most production-ready model yet. The fastest 4K video generation in the world with built-in native dialogue. Here’s what’s new 🧵 1/9

Introducing LTX-2.3 Our most production-ready model yet. The fastest 4K video generation in the world with built-in native dialogue. Here’s what’s new 🧵 1/9

LTX Studio

678,210 views • 8 months ago

Introducing Reframe. Expand your image or get closer to the details, in any aspect ratio.

Introducing Reframe. Expand your image or get closer to the details, in any aspect ratio.

Reve

297,198 views • 3 months ago

A look at the video outpainting workflow in ComfyUI using LTX 2.3. 🎥 Instead of cropping your 16:9 footage for vertical, use this IC-LoRA setup to generate the missing space and keep your original frame. Shout out to Mohamed Oumoumad for their open source contribution. Link to workflow below! 👇

A look at the video outpainting workflow in ComfyUI using LTX 2.3. 🎥 Instead of cropping your 16:9 footage for vertical, use this IC-LoRA setup to generate the missing space and keep your original frame. Shout out to Mohamed Oumoumad for their open source contribution. Link to workflow below! 👇

ComfyUI

19,041 views • 6 months ago

Video to Video now in LTX Studio. Choose Pose, Depth, or Edges. Add a prompt and starting image. Generate a new video with the structure you choose to carry over, powered by LTX-2.3.

Video to Video now in LTX Studio. Choose Pose, Depth, or Edges. Add a prompt and starting image. Generate a new video with the structure you choose to carry over, powered by LTX-2.3.

LTX.io

339,176 views • 5 months ago

If the engine is strong enough, you should be able to build real products on top of it. That's the whole point of LTX-2.3. Introducing LTX Desktop. A fully local, open-source video editor running directly on the LTX engine, optimized for NVIDIA GPUs and compatible hardware.

If the engine is strong enough, you should be able to build real products on top of it. That's the whole point of LTX-2.3. Introducing LTX Desktop. A fully local, open-source video editor running directly on the LTX engine, optimized for NVIDIA GPUs and compatible hardware.

LTX

955,052 views • 8 months ago

Introducing Smart Reframe in Cardboard One video → horizontal, vertical, square Cardboard finds the subject, keeps them in frame, and gives you the format you asked for. No crop box. No keyframes. Only 1-prompt. Try it on: cardboard (dot) ai

Introducing Smart Reframe in Cardboard One video → horizontal, vertical, square Cardboard finds the subject, keeps them in frame, and gives you the format you asked for. No crop box. No keyframes. Only 1-prompt. Try it on: cardboard (dot) ai

Saksham

10,080 views • 4 months ago

LTX-2.3 is a major upgrade. It’s a production-ready multimodal engine - designed to be built on. Here’s what’s new 🧵 1/7

LTX-2.3 is a major upgrade. It’s a production-ready multimodal engine - designed to be built on. Here’s what’s new 🧵 1/7

LTX

850,080 views • 8 months ago

tvOS 18.2 Developer Beta 1 introduces the ability for Apple TV to automatically detect the best aspect ratio for your television or projector. If you have an anamorphic lens or your television's aspect ratio is not detected, users will have the ability to manually choose from the following options: 16:9, 21:9, 2.37:1, 2.39:1, 2.40:1, DCI 4K, 32:9

tvOS 18.2 Developer Beta 1 introduces the ability for Apple TV to automatically detect the best aspect ratio for your television or projector. If you have an anamorphic lens or your television's aspect ratio is not detected, users will have the ability to manually choose from the following options: 16:9, 21:9, 2.37:1, 2.39:1, 2.40:1, DCI 4K, 32:9

Sigmund Judge

29,552 views • 2 years ago

Quick FOV talk on why you shouldn't use 90 FOV on 16:9 and why 74 FOV on 16:9 is a viable thing to do. FOV isn't just 1 slider, it's affected by the aspect ratio. Especially important for Console Players that cannot change their aspect ratio.

Quick FOV talk on why you shouldn't use 90 FOV on 16:9 and why 74 FOV on 16:9 is a viable thing to do. FOV isn't just 1 slider, it's affected by the aspect ratio. Especially important for Console Players that cannot change their aspect ratio.

Noob

45,328 views • 1 year ago

Today, we open-source PrunaVAED, a faster drop-in replacement decoder for video generation with LTX-2.3! - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? ~1.7-2.1x faster decoder & ~50% lower peak VRAM - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? Near-original visual quality & no changes to the latent encoding - 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸? We pruned, trained & distilled video decoders to maximize efficiency of the LTX-2.3 series from Lightricks Want to try the fast open-source integration? Check it here on Diffusers: Want to try the fastest video generation endpoint? Check p-video here on API:

Today, we open-source PrunaVAED, a faster drop-in replacement decoder for video generation with LTX-2.3! - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? ~1.7-2.1x faster decoder & ~50% lower peak VRAM - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? Near-original visual quality & no changes to the latent encoding - 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸? We pruned, trained & distilled video decoders to maximize efficiency of the LTX-2.3 series from Lightricks Want to try the fast open-source integration? Check it here on Diffusers: Want to try the fastest video generation endpoint? Check p-video here on API:

Pruna AI

26,082 views • 3 months ago

(1/13) We’ve been working on something special ✨ Introducing LTX Video, Lightricks’ new open-source, community-driven model for video generation. Create breathtaking videos in moments, blazing past traditional playback speeds—this is LTX Video. Learn more below.

(1/13) We’ve been working on something special ✨ Introducing LTX Video, Lightricks’ new open-source, community-driven model for video generation. Create breathtaking videos in moments, blazing past traditional playback speeds—this is LTX Video. Learn more below.

LTX.io

145,210 views • 1 year ago

AI video just got more powerful LTX Studio just made clip extension ridiculously practical: with LTX-2.3, you can keep pushing any generated or uploaded video 12 seconds at a time, all the way up to 60 seconds That removes one of the biggest limitations in AI video Examples below 👇🏻

AI video just got more powerful LTX Studio just made clip extension ridiculously practical: with LTX-2.3, you can keep pushing any generated or uploaded video 12 seconds at a time, all the way up to 60 seconds That removes one of the biggest limitations in AI video Examples below 👇🏻

Amira Zairi

25,381 views • 6 months ago

Your clips can now keep go... Extend ANY video with LTX-2.3, generated or uploaded, up to 12 seconds at a time, 60 seconds total. Live now in LTX Studio.

Your clips can now keep go... Extend ANY video with LTX-2.3, generated or uploaded, up to 12 seconds at a time, 60 seconds total. Live now in LTX Studio.

LTX.io

22,303,845 views • 6 months ago

Cancel your AI video subscriptions immediately. LTX-2.3 just dropped their production-grade API, giving you direct access to the world’s most downloaded video engine without needing a local GPU. Save your money. The API era is officially here. Full breakdown:

Cancel your AI video subscriptions immediately. LTX-2.3 just dropped their production-grade API, giving you direct access to the world’s most downloaded video engine without needing a local GPU. Save your money. The API era is officially here. Full breakdown:

Farhan

60,584 views • 7 months ago

Most AI video tools stop at prompting, but LTX goes a layer deeper. Introducing the new LTX Trainer. Train LoRAs and IC-LoRAs across video, audio, cross-modal, and reference-conditioned workflows from a single framework. Plus: • New agentic skill • Flexible conditioning • Free IC-LoRAs • Fully open source Most models are generic. The best ones become yours. GitHub: Documentation: HuggingFace:

Most AI video tools stop at prompting, but LTX goes a layer deeper. Introducing the new LTX Trainer. Train LoRAs and IC-LoRAs across video, audio, cross-modal, and reference-conditioned workflows from a single framework. Plus: • New agentic skill • Flexible conditioning • Free IC-LoRAs • Fully open source Most models are generic. The best ones become yours. GitHub: Documentation: HuggingFace:

LTX.io

6,487,437 views • 4 months ago

Introducing the new Hive App. We rebuilt the entire product from the ground up: - New Dashboard - New Docs - New Playground 9 data providers. 600+ tools. 14 categories. One API key. Every crypto data source your AI agent needs in a single integration.

Introducing the new Hive App. We rebuilt the entire product from the ground up: - New Dashboard - New Docs - New Playground 9 data providers. 600+ tools. 14 categories. One API key. Every crypto data source your AI agent needs in a single integration.

Hive Intelligence

10,499 views • 6 months ago

1/ Text2Video was yesterday; Audio2Video is the new big thing! Following the huge success of their open-source text-to-video model, LTX Studio is following up with another massive release: Audio-to-Video. Here are some outstanding examples🧵

1/ Text2Video was yesterday; Audio2Video is the new big thing! Following the huge success of their open-source text-to-video model, LTX Studio is following up with another massive release: Audio-to-Video. Here are some outstanding examples🧵

Chubby♨️

28,330 views • 9 months ago

Ovi is out on Hugging Face Twin Backbone Cross-Modal Fusion for Audio-Video Generation Ovi is a veo-3 like, video+audio generation model that simultaneously generates both video and audio content from text or text+image inputs. Video+Audio Generation: Generate synchronized video and audio content simultaneously Flexible Input: Supports text-only or text+image conditioning 5-second Videos: Generates 5-second videos at 24 FPS, area of 720×720, at various aspect ratios (9:16, 16:9, 1:1, etc)

Ovi is out on Hugging Face Twin Backbone Cross-Modal Fusion for Audio-Video Generation Ovi is a veo-3 like, video+audio generation model that simultaneously generates both video and audio content from text or text+image inputs. Video+Audio Generation: Generate synchronized video and audio content simultaneously Flexible Input: Supports text-only or text+image conditioning 5-second Videos: Generates 5-second videos at 24 FPS, area of 720×720, at various aspect ratios (9:16, 16:9, 1:1, etc)

AK

23,082 views • 1 year ago