Generate
Back to Models
Models/lightricks/video · text-to-video · image-to-video · first-last-frameMachGen Hosted

LTX 2.3 Pro

LTX 2.3 Pro combines high-resolution cinematic video with prompt-level camera direction and synchronized native audio. On MachGen it creates 16:9 video from text, a starting image, or a first-and-last-frame pair at 1080p, 2K, or 4K for 6, 8, or 10 seconds, with built-in prompt enhancement.

Current MachGen support
Text to VideoImage to VideoFrame to Frame6 / 8 / 10s1080p / 2K / 4KOptional audioPrompt enhancementSeed control
Starting at $0.007 / output s
540p$0.007/s
720p$0.015/s
1080p$0.03/s
1440p$0.06/s
2160p$0.10/s
Live public pricebookSee full pricebook

Overview

LTX 2.3 Pro combines high-resolution cinematic video, directorial prompt control, detailed motion, and synchronized native audio. It is suited to commercial shots, narrative sequences, and production concepts that benefit from controlled opening and ending compositions.

On MachGen it creates 16:9 video from text, a starting image, or a first-and-last-frame pair. Choose 6, 8, or 10 seconds at 24 fps and 1080p, 2K, or 4K, with native audio and optional prompt enhancement in every exposed mode.

Model guide

Why choose LTX 2.3 Pro

Key strengths

  • Production-oriented video with sharp detail, strong prompt adherence, and synchronized native audio.
  • Supports text, starting-image, and first-to-last-frame workflows on MachGen.
  • High-resolution output makes it suitable for shots intended for editing, grading, or larger displays.

Good fit for

  • Cinematic product films, branded scenes, and polished campaign shots.
  • Dialogue, ambience, or sound-effect-driven clips.
  • Controlled transitions between designed opening and closing frames.
Supported on MachGen

Inputs and output settings

This table reflects the model routes and controls currently exposed by MachGen.

ModeRequired inputAvailable settings
Text to VideoText promptResolution: 1080p, 2K, 4K
Aspect ratio: 16:9
Duration: 6s, 8s, 10s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt enhancement
Image to VideoText prompt and source image; optional end frameResolution: 1080p, 2K, 4K
Aspect ratio: 16:9
Duration: 6s, 8s, 10s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt enhancement
First & Last FrameText prompt, start frame, and end frameResolution: 1080p, 2K, 4K
Aspect ratio: 16:9
Duration: 6s, 8s, 10s
Frame rate: 24fps
Optional generated audio
Seed control
Prompt enhancement
Workflow

Using LTX 2.3 Pro

  1. Choose a supported generation mode in Playground.
  2. Add the required prompt and source or reference assets.
  3. Select output settings from the controls shown for that mode.
  4. Generate, then inspect the returned asset before reusing the settings through the API.

Practical guidance

  • Describe the subject, action or composition, environment, and visual direction in a clear order.
  • For image animation, describe the intended motion and camera behavior instead of repeating what is already visible.
  • Use compatible start and end frames, then describe the transition between them.
  • When audio is enabled, include any dialogue, ambience, or sound cues that matter to the scene.

Modes available on MachGen

  • Text to video - create a clip from a scene description.
  • Image to video - animate a starting image with prompt-directed motion.
  • First and last frame - provide two images to control the opening and landing compositions.
  • Output controls - 1080p, 2K, or 4K landscape output at 24 fps, with 6, 8, or 10 second durations.

Audio-to-video, retake, and extend exist in the upstream LTX Pro product family but are not exposed by this MachGen catalog entry.

Prompting notes

  • Write one continuous present-tense paragraph; longer, specific prompts usually win.
  • Name camera behavior in text or use the camera_motion selector.
  • Call out atmosphere - light quality, weather, textures - and prefer active verbs.
Best results

How to get better LTX 2.3 Pro results

  • Write events in time order: establish the opening, describe the main action, then state how the shot ends.
  • Include spoken words, sound effects, ambience, and music direction in the prompt when audio is enabled.
  • Use start and end frames with compatible subjects, framing, and lighting so the transition has a plausible path.
  • Validate motion and composition at 1080p before spending on a 2K or 4K final.
Limits

Limits and availability

  • MachGen admits only the modes and settings listed above for this catalog model.
  • Source assets must finish uploading before a request can be submitted.
  • Generated results can vary between requests, including when the same prompt and settings are reused.
  • LTX 2.3 Pro runs on MachGen-managed inference infrastructure rather than being forwarded to a provider API.
Learn more

Learn more

For model background, technical details, and architecture, see the official LTX 2.3 model page.

Try this model in the MachGen Playground.

Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.

Pricing

LTX 2.3 Pro pricing

See Pricing for currently published MachGen rates. When available, the Playground estimate reflects the selected task and output settings.

On MachGen

LTX 2.3 Pro on MachGen

Deployment: MachGen Hosted. LTX 2.3 Pro runs on MachGen-managed inference infrastructure rather than being forwarded to a provider API.

The Playground and API sections on this page list the inputs and output settings exposed for this model.