Available now

LTX-2.3 Quality: image to video

By Lightricks

LTX-2.3 Quality is Lightricks' LTX-2.3 tuned for quality with few settings: video with sound from a prompt or a start image, sized by frame count.

Model ID
Maker
Lightricks

Input

Fields marked * are required. Review the price before generating.

The prompt to guide the video generation.

Example prompt. Edit it or write your own.

The starting image.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

The size of the generated video.

Additional settings

Defaults to 15 and can be increased up to 30.

Classifier-free guidance scale. The default is tuned for fast, high-quality generation.

Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.

Conditioning strength on the start image. 1.0 = exact first-frame match, lower = more freedom for the model.

The negative prompt to steer generation away from.

Random seed for reproducibility. If None, a random seed is chosen.

Whether to enable prompt expansion.

Price$0.01 / megapixel

You sign up first. Your settings are kept.

About this model

Overview

LTX-2.3 Quality makes clips of 9 to 481 frames in square, square HD, or 4:3 and 16:9 in landscape or portrait. Sound is on by default; turn it off to get an MP4 with no audio track.

Its guidance and step defaults are already tuned, so most runs need only a prompt. In the image mode, image strength sets how closely the first frame matches your picture: 1 is an exact match, lower values let the scene move away from it.

What you can build

  • Short scenes with matching ambient sound
  • Product stills opened into a moving shot
  • Clips cut to an exact frame count for an edit
  • Portrait 16:9 clips for stories and reels

Prompting tips

  • Start with the defaults; raise the steps toward 30 only when fine detail looks soft.
  • Set image strength to 1 when the first frame must be your exact picture, such as a product shot.
  • Describe sound in the prompt, such as rain on a tin roof, and switch audio off when you will score the clip yourself.

What to check

Inspect faces during movement, background stability and sound transitions.

Inputs

  • Prompt (required): The prompt to guide the video generation.
  • Image (required): The URL of the starting image.
  • Number of Frames (optional): The number of frames to generate. From 9 to 481.
  • Resolution (optional): The size of the generated video. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Number of Inference Steps (optional): Number of inference steps. Defaults to 15 and can be increased up to 30.
  • Guidance Scale (optional): Classifier-free guidance scale. The default is tuned for fast, high-quality generation. From 1 to 20.
  • Generate Audio (optional): Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.
  • Image Strength (optional): Conditioning strength on the start image. 1.0 = exact first-frame match, lower = more freedom for the model.
  • Negative Prompt (optional): The negative prompt to steer generation away from.
  • Seed (optional): Random seed for reproducibility. If None, a random seed is chosen.
  • Enable Prompt Expansion (optional): Whether to enable prompt expansion.
  • Video Write Mode (optional): The write mode of the generated video. Options: fast, balanced, small.

Output and limits

  • Resolutions: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Sound can be generated together with the video.
  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1 megapixel: $0.01 / megapixel