Lightricks/

LTX-2.3-Fast

Partner

$0.06 / second

*

LTX-2.3 Fast is Lightricks' lowest-cost video model. It generates landscape or portrait video from text or a first frame, up to 4K at 24–50 fps, with synchronized audio and clips up to 20 seconds.

Public

api

Input

Prompt

Text prompt describing the video, or how to animate the image

You need to log in to use this model

Log In

Settings

ImageUpload Image File

Please upload an image file

Last frameUpload Image File

Please upload an image file

Resolution

Output resolution as WIDTHxHEIGHT, in 16:9 or 9:16. Price per second by the short side: 720p $0.03, 1080p $0.06, 1440p $0.12, 4K $0.24

Duration

Duration in seconds. Above 10 seconds needs 720p or 1080p at 24 or 25 fps

Fps

Frame rate in frames per second

Generate Audio

Whether to generate an audio track matching the scene

Camera Motion

Camera motion effect applied to the video

Output

Model Information

LTX-2.3 Fast is the speed- and cost-optimized variant of LTX-2.3 by Lightricks, and the lowest-cost video model on DeepInfra. It turns a text prompt or a starting image into landscape or portrait video up to 4K, at cinematic frame rates, with an AI-generated audio track that matches the scene.

Text-to-video and image-to-video in 16:9 and 9:16
Up to 4K, at 24, 25, 48 or 50 fps
Clips from 6 to 20 seconds
Synchronized audio, or silent video with generate_audio: false
Camera motion presets: dolly in/out/left/right, jib up/down, static, focus shift
First and last frame control for image-to-video

Resolutions

	16:9	9:16
720p	1280x720	720x1280
1080p	1920x1080	1080x1920
1440p	2560x1440	1440x2560
4K	3840x2160	2160x3840

Durations and frame rates

Resolution	24 or 25 fps	48 or 50 fps
720p, 1080p	6 to 20 s, in even steps	6, 8 or 10 s
1440p, 4K	6, 8 or 10 s	6, 8 or 10 s

Image-to-video

Pass image_url to animate an image from its first frame, and optionally last_frame_url to set where the clip ends. Each takes an https URL (up to 15 MB), a base64 data URI or a file upload (up to 7 MB encoded), in PNG, JPEG or WebP. Image-to-video costs the same as text-to-video.