LTX-2.3 Text-to-Video generates cinematic video clips directly from text prompts. Built on an upgraded 2.3B architecture, it delivers sharper temporal consistency, faster synthesis, and more precise motion control than previous LTX versions. Ideal for concept visualization, story beats, and prompt-driven animation.
About this model
LTX-2.3 Text-to-Video generates cinematic video clips directly from text prompts. Built on an upgraded 2.3B architecture, it delivers sharper temporal consistency, faster synthesis, and more precise motion control than previous LTX versions.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.0208 / sec | Highly competitive for 720p |
Highly competitive for 720p
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Text prompt describing the video. | A high-speed train suddenly bursts through the wall of a quiet apartment building and races straight through the living rooms and hallways. Furniture flies everywhere as the train blasts through multiple floors before exiting the other side of the building. |
| Duration | int | Duration of the generated video in seconds. | 5 |
| Aspect Ratio | Enum (2 options) | Aspect ratio of the generated video. | 16:9 |
| Resolution | Enum (3 options) | The resolution of the generated video. | 720p |
| Seed | int | Random seed. -1 for random. | -1 |
Text prompt describing the video.
A high-speed train suddenly bursts through the wall of a quiet apartment building and races straight through the living rooms and hallways. Furniture flies everywhere as the train blasts through multiple floors before exiting the other side of the building.Duration of the generated video in seconds.
5Aspect ratio of the generated video.
16:9The resolution of the generated video.
720pRandom seed. -1 for random.
-1Developer documentation
Describe your scene in detail, including lighting, camera movement, and character actions. Higher quality is achieved with descriptive prompts.
Frequently asked
The model supports up to 20 seconds of video generation.
480p, 720p, and 1080p.