LTX 2.3
LTX 2.3 delivers sharper detail, cleaner audio, stronger motion, and native portrait video in one advanced generation model. Built for high-quality video creation, it improves prompt adherence, image-to-video consistency, and overall production-ready output.
What is LTX 2.3?
What LTX 2.3 can do
Native portrait video
Generates vertical footage directly, so Reels and Shorts do not need cropping from a landscape render.
Sharper detail and cleaner audio
Improved fidelity in both picture and sound compared with earlier LTX releases.
Consistent image-to-video
Holds your source image's detail as it animates, so the clip still looks like the shot you uploaded.
How to use LTX 2.3 on MagicShot
Open a tool
Head to Image to Video or any video tool. No model settings to configure.
Add your prompt
Describe what you want, or upload your own media to work from. Plain language is all it takes.
Generate and download
LTX 2.3 returns your video in seconds, ready to download and use commercially on paid plans.
Tools powered by LTX 2.3
One subscription. Every top video model.
LTX 2.3 is one of 24 AI video models built into MagicShot. Instead of paying for, learning, and switching between a different app for each one, you get them all in a single place. We benchmark the newest models as they ship and swap in the best, so your results keep improving and everything you make is yours to use commercially.
Other AI video models on MagicShot
Wan 3.0
Featuredalibaba
Wan 3.0 is Alibaba Tongyi Lab's text-to-video model, built to turn a written prompt, a photo, or a reference clip into a finished video with sound already in it. Inside MagicShot, it runs on paid plans for product demos, social clips, and short marketing videos.
View Wan 3.0 →Seedance 2.5
FeaturedBytedance
Seedance 2.5 is ByteDance's flagship multimodal video model, available inside MagicShot on a paid plan. It turns a text prompt plus up to 50 image, video and audio references into a single clip of up to 30 seconds, with dialogue, music and sound effects generated alongside the picture.
View Seedance 2.5 →Wan 3.0 Prime
FeaturedAlibaba
Wan 3 Prime is the fast tier of Alibaba's Wan 3.0 video model, built for text-to-video and image-to-video generation. It turns a prompt or a single photo into a video clip up to 30 seconds long, complete with a matching audio track.
View Wan 3.0 Prime →MiniMax H3
FeaturedMiniMax
MiniMax H3 is an omni-modal video model built by MiniMax that reads text, images, video, and audio together and turns them into finished video clips. On MagicShot, it works as a text-to-video and image-to-video engine that renders motion, on-screen text, and native stereo sound in a single generation.
View MiniMax H3 →Gemini Omni 1.1
FeaturedGemini Omni 1.1 is Google's fast multimodal video model, built to turn a text prompt or a single photo into a moving clip with sound already baked in. Inside MagicShot, it runs as the speed option for text-to-video and image-to-video, so you get a usable draft in seconds instead of minutes.
View Gemini Omni 1.1 →LTX 2.5
Featuredlightricks
LTX 2.5 is an AI video model from Lightricks, built for speed, that turns a text prompt or a still image into a clip with synchronized audio. Inside MagicShot on a paid plan, it outputs MP4 video in portrait or landscape, up to 20 seconds long, with 4K resolution available.
View LTX 2.5 →LTX 2.3 FAQ
Ready to create something magical?
Join 500,000+ creators making images, videos and voiceovers in seconds.
