LTX-2.3 22B

Extend video with audio using LTX-2.3

Inference$ Commercial useFrom 21 credits per run

About LTX-2.3 22B

Extend video with audio using LTX-2.3

Pricing

A run with the default settings costs 21 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

prompttextarearequired

The prompt to generate the video from.

video_urlfilerequired

The URL of the video to extend.

end_image_urlfile

The URL of the image to use as the end of the extended video.

num_framesintegerdefault: 121

The number of frames to generate.

video_sizeselectdefault: "auto"

The size of the generated video.

Options: auto, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

generate_audiobooleandefault: true

Whether to generate audio for the video.

use_multiscalebooleandefault: true

Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.

match_input_fpsbooleandefault: true

When true, match the output FPS to the input video's FPS instead of using the default target FPS.

fpsnumberdefault: 24

The frames per second of the generated video.

num_inference_stepsintegerdefault: 40

The number of inference steps to use.

video_cfg_scalenumberdefault: 3

The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.

video_stg_scalenumberdefault: 0

The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.

video_rescaling_scalenumberdefault: 0.7

The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.

video_modality_scalenumberdefault: 3

The modality scale for the video. Controls the ratio between video and audio modalities.

audio_cfg_scalenumberdefault: 7

The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.

audio_stg_scalenumberdefault: 0

The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.

audio_rescaling_scalenumberdefault: 0.7

The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.

audio_modality_scalenumberdefault: 3

The modality scale for the audio. Controls the ratio between video and audio modalities.

gradient_estimation_gammanumberdefault: 2

The gamma of gradient estimation during denoising. Set to 0 to disable.

use_restart_samplingbooleandefault: false

Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.

schedulerselectdefault: "ltx2"

The scheduler to use.

Options: ltx2, linear_quadratic, beta

accelerationselectdefault: "regular"

The acceleration level to use.

Options: none, regular, high, full

camera_loraselectdefault: "none"

The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.

Options: dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, none

camera_lora_scalenumberdefault: 1

The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.

negative_prompttextareadefault: "news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static"

The negative prompt to generate the video from.

seedinteger

The seed for the random number generator.

enable_prompt_expansionbooleandefault: true

Whether to enable prompt expansion.

enable_safety_checkerbooleandefault: true

Whether to enable the safety checker.

video_output_typeselectdefault: "X264 (.mp4)"

The output type of the generated video.

Options: X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif)

video_qualityselectdefault: "high"

The quality of the generated video.