lightricks/ltx-2.3-pro

OfficialView on Replicate →

High-fidelity video generation with portrait support, audio-to-video, retake, and extend. Text, image, and audio-driven creation up to 4K at 50 FPS.

Capabilities

Reference Images

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`prompt`*	string	Text prompt describing the video to generate	`—`	—
`aspect_ratio`	string	Aspect ratio of the generated video	`"16:9"`	16:99:16
`audio`	string(uri)	Input audio file for audio_to_video task	`—`	—
`camera_motion`	string	Camera motion effect to apply to the generated video. Use 'none' for no camera motion.	`"none"`	nonedolly_indolly_outdolly_leftdolly_rightjib_upjib_downstaticfocus_shift
`duration`	integer	Duration of the video in seconds	`6`	6810
`extend_mode`	string	Where to extend the video. Used for extend task.	`"end"`	startend
`fps`	integer	Frame rate in frames per second	`25`	24254850
`generate_audio`	boolean	Generate audio for the video. Used for text_to_video and image_to_video tasks.	`true`	—
`image`	string(uri)	First frame image for image-to-video generation	`—`	—
`last_frame_image`	string(uri)	Last frame image for image-to-video generation. When provided, the video interpolates between the first frame and this last frame.	`—`	—
`resolution`	string	Resolution quality of the generated video. Only 1080p is supported for audio_to_video, retake, and extend tasks.	`"1080p"`	1080p2k4k
`retake_duration`	number	Duration in seconds of the section to edit. Must be at least 2 seconds. Used for retake task.	`2`	min: 2
`retake_mode`	string	What to replace in the retake section. Used for retake task.	`"replace_audio_and_video"`	replace_audioreplace_videoreplace_audio_and_video
`retake_start_time`	number	Start time in seconds of the section to edit. Used for retake task.	`0`	min: 0
`task`	string	The generation task to perform	`"text_to_video"`	text_to_videoimage_to_videoaudio_to_videoretakeextend
`video`	string(uri)	Input video for retake or extend tasks	`—`	—

promptrequiredstring

Text prompt describing the video to generate

aspect_ratiostring

Aspect ratio of the generated video

Default: "16:9"

16:99:16

audiostring

Input audio file for audio_to_video task

camera_motionstring

Camera motion effect to apply to the generated video. Use 'none' for no camera motion.

Default: "none"

nonedolly_indolly_outdolly_leftdolly_rightjib_upjib_downstaticfocus_shift

durationinteger

Duration of the video in seconds

Default: 6

6810

extend_modestring

Where to extend the video. Used for extend task.

Default: "end"

startend

fpsinteger

Frame rate in frames per second

Default: 25

24254850

generate_audioboolean

Generate audio for the video. Used for text_to_video and image_to_video tasks.

Default: true

imagestring

First frame image for image-to-video generation

last_frame_imagestring

Last frame image for image-to-video generation. When provided, the video interpolates between the first frame and this last frame.

resolutionstring

Resolution quality of the generated video. Only 1080p is supported for audio_to_video, retake, and extend tasks.

Default: "1080p"

1080p2k4k

retake_durationnumber

Duration in seconds of the section to edit. Must be at least 2 seconds. Used for retake task.

Default: 2min: 2

retake_modestring

What to replace in the retake section. Used for retake task.

Default: "replace_audio_and_video"

replace_audioreplace_videoreplace_audio_and_video

retake_start_timenumber

Start time in seconds of the section to edit. Used for retake task.

Default: 0min: 0

taskstring

The generation task to perform

Default: "text_to_video"

text_to_videoimage_to_videoaudio_to_videoretakeextend

videostring

Input video for retake or extend tasks

Version: 2560a82a0a6fUpdated: 8/1/202654.0K runs