Consistency controls
Video CFG Scale (1 to 20) and Video STG Scale (0 to 20) give more consistent and focused video at higher values.
Create a video from a description
Generate video with audio from text using LTX-2.3
Opens the video studio with LTX-2.3 22B · Text→Video ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What it makes
Create a video from a description
Turns a written description into a short video.
What you need
What you get
A short video clip
LTX-2.3 22B turns a text description into a video and can create audio for it as well. It has four scale controls of its own: Video CFG Scale, Video STG Scale, Video Rescaling Scale and Video Modality Scale. What comes back is a video.
The text description is the only required input. Number of Frames runs from 9 to 481, FPS (frames per second) from 1 to 60, and Video Size starts at landscape 16:9. Video CFG Scale is a guidance setting that runs from 1 to 20. Video STG Scale (Spatiotemporal Guidance) runs from 0 to 20. Higher values give more consistent and focused video. Video Rescaling Scale (0 to 1) sets the ratio between the Video CFG Scale and Video STG Scale guidance. Video Modality Scale (0 to 10) controls the ratio between video and audio. Generate Audio and Use Multi-Scale are on to begin with.
LTX-2.3 22B costs 100 credits. LTX-2.3 22B Distilled costs the same and has a Camera LoRA option instead of these scale controls.
Same job: create a video from a description. Compare before you choose.
MiniMax Video-01 turns text prompts into cinematic 720p clips in seconds, with smooth motion and dynamic camera work. No filming or editing skills needed.
MiniMax Video-01-Live is a text-to-video generation model that creates high-quality MP4 video clips with built-in prompt optimization for improved visual coherence and motion fidelity.
MiniMax Hailuo-2.3 Pro is an advanced text-to-video generation model that creates high-quality 1080p video with strong prompt understanding, cinematic motion, and support for detailed action and audio-aware prompts.
PixVerse v5 is a high-quality text-to-video generation model that creates video clips from text prompts, with support for multiple resolutions including 360p, 540p, 720p, and 1080p.
Video CFG Scale (1 to 20) and Video STG Scale (0 to 20) give more consistent and focused video at higher values.
Video Modality Scale (0 to 10) controls the ratio between video and audio.
Generate Audio makes audio for the video and is on to begin with.
Write a text description of the scene. It is the only required input.
Change Number of Frames, FPS, Video Size or Generate Audio if you want. The scales are optional.
Run LTX-2.3 22B for 100 credits and receive your video.
Describe a scene and get a video back.
Generate Audio is on to begin with, so the video can come with audio made from your text.
Quick answers to help you get the most out of LTX-2.3 22B · Text→Video in FunAI Studio.