LTX Video (preview)

LTX Video (preview) is a LTX route built for image-to-video generation. It turns a source image and motion direction into a moving sequence that develops the supplied frame, giving creators a focused endpoint instead of forcing one generic workflow across materially different production tasks. The route belongs to a family known for audio-visual timing, cinematic motion, and shot-level controllability, so it is best evaluated as a creative system for intentional shots and assets rather than as a one-click novelty generator.

Use this endpoint when the input contract and deliverable match that job exactly. Its documented controls include seed (The seed to use for random number generation); guidance_scale (The guidance scale to use); num_inference_steps (The number of inference steps to take). Together, these controls help teams plan predictable iterations, compare outputs under stable settings, and connect generation to iterative film, advertising, and social-video workflows without hiding the operational choices that shape the result.

Highlights

• Purpose-built Image-to-video generation. The route accepts a source image and motion direction and produces a moving sequence that develops the supplied frame; its interface is scoped to that transformation, keeping source assets and creative intent explicit.
• Creative direction. Prompts can describe subject behavior, composition, camera intent, lighting, material, atmosphere, and temporal progression so the result is driven by a shot plan rather than isolated keywords.
• Route-specific control. The request exposes seed (The seed to use for random number generation); guidance_scale (The guidance scale to use); num_inference_steps (The number of inference steps to take), allowing the same concept to be tested systematically while preserving a repeatable production setup.
• Pipeline-ready output. The generated media asset is returned through the documented asynchronous output contract, which suits review queues, batch iteration, and downstream automation. Editors can review pacing, continuity, lens language, choreography, transitions, temporal artifacts, soundtrack alignment, color response, delivery framing, and cut compatibility before approval.

Pricing

When to Use

Prompt Guide

Start with the desired result, then describe the source relationship, subject action, composition or camera behavior, lighting, style, and timing. For image-to-video generation, state what must remain stable as clearly as what should change. Use only fields exposed by the schema; the example below is structurally valid for this route.

{
  "prompt": "A lone astronaut in a white spacesuit with gold-tinted visor drifts weightlessly through a sleek, cylindrical corridor of a spaceship. Their movements are slow and graceful as they gently push off the metallic walls with their gloved hands, rotating slightly as they float from right to left across the frame. The corridor features brushed aluminum panels with blue LED strips running along the ceiling, casting a cool glow on the astronaut's suit. Various cables, pipes, and control panels line the walls. The camera follows the astronaut's movement in a handheld style, slightly swaying and adjusting focus, maintaining a medium shot that captures both the astronaut and the corridor's depth. Small particles of dust catch the light as they float in the zero-gravity environment. The scene appears cinematic, with lens flares occasionally reflecting off the metallic surfaces and the astronaut's visor.",
  "image": "https://static.sandbase.ai/examples/lightricks/ltx-video/image-to-video/input_image_0.jpg",
  "seed": 1,
  "guidance_scale": 3,
  "num_inference_steps": 30
}

Technical Specs

Related Models

• lightricks/ltx-video