MODEL ID lightricks:ltx@2

live

LTX-2

by Lightricks January 5, 2026

LTX-2 is an open-source multimodal video foundation model that generates synchronized video and audio from text or image prompts. It produces high-quality motion sequences with native 4K resolution and smooth temporal coherence, making it suitable for creative video generation, production workflows, and audiovisual storytelling.

API Options

Platform-level options for task execution and delivery.

taskType string required value: videoInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Video output type.

Allowed values 1 value

outputFormat string default: MP4

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

`MP4`: Widely supported video container (H.264), recommended for general use.
`WEBM`: Optimized for web delivery.
`MOV`: QuickTime format, common in professional workflows (Apple ecosystem).

Allowed values 3 values

outputQuality integer min: 20 max: 99 default: 95: Compression quality of the output. Higher values preserve quality but increase file size.

webhookURL string URI

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more 1 resource

Webhooks
PLATFORM

deliveryMethod string default: async

Determines how the API delivers task results.

Allowed values 1 value

: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. Required for long-running tasks like video generation.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string URI

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

safety object

Content safety checking configuration for video generation.

Properties 2 properties

safety » checkContent checkContent boolean default: false: Enable or disable content safety checking. When enabled, defaults to fast mode.

safety » mode mode string default: none

Safety checking mode for video generation.

Allowed values 3 values

: Disables checking.
: Checks key frames.
: Checks all frames.

ttl integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults integer min: 1 max: 4 default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Inputs

Input resources for the task (images, audio, etc). These must be nested inside the inputs object.

inputs » frameImages frameImages array of strings or objects items: 1

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target frame position.

The frameImages parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. This is different from referenceImages, which provide overall visual guidance without constraining specific timeline positions.

When the frame parameter is omitted, automatic distribution rules apply:

1 image: Used as the first frame.

Examples 2 examples

Shorthand format: When you don't need to specify a frame position, you can pass a plain image input directly.

"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]

Object format: When you need to specify a frame position, use an object with image and frame.

"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]

Format 1: string[]

string: Image input (UUID, URL, Data URI, or Base64).

Format 2: object[] 2 properties

inputs » frameImages » image image string required: Image input (UUID, URL, Data URI, or Base64).

inputs » frameImages » frame frame object

Target frame position for the image. This model only supports the first frame.

Allowed values 2 values

: First frame of the video.
: Frame index 0 (first frame).

Generation Parameters

Core parameters for controlling the generated content.

model string required value: lightricks:ltx@2

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required

Text prompt describing elements to include in the generated output.

Learn more 2 resources

negativePrompt string

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

Learn more 1 resource

Text To Image: Prompts Guiding The Generation
GUIDE

width integer min: 128 max: 2048 step: 64

Width of the generated media in pixels.

Learn more 2 resources

height integer min: 128 max: 2048 step: 64

Height of the generated media in pixels.

Learn more 2 resources

duration integer min: 1 max: 20: Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

fps integer min: 1 max: 120 default: 25: Frames per second for video generation. Higher values create smoother motion but require more processing time.

steps integer min: 1 max: 100 default: 40

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

Learn more 1 resource

Text To Image: Steps Trading Quality For Speed
GUIDE

CFGScale float min: 1 max: 20 step: 0.01 default: 4

Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.

Learn more 1 resource

Text To Image: Cfg Scale Balancing Creativity And Control
GUIDE

Settings

Technical parameters to fine-tune the inference process. These must be nested inside the settings object.

settings » enhancePrompt enhancePrompt boolean default: true: Enable automatic prompt enhancement for cinematic results.

taskType string required value: videoInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

videoUUID string required UUID v4: UUID of the output video.

videoURL string URI: URL of the output video.

videoBase64Data string: Base64-encoded video data.

videoDataURI string URI: Data URI of the output video.

seed integer: The seed used for generation. If none was provided, shows the randomly generated seed.

NSFWContent boolean: Flag indicating if NSFW content was detected.

cost float: Task cost in USD. Present when includeCost is set to true in the request.

Text to Video

Bioluminescent Tidepool Observatory

Request

{
  "taskType": "videoInference",
  "taskUUID": "4d89f0f5-1277-48ee-875d-58e07a4b09d3",
  "model": "lightricks:ltx@2",
  "positivePrompt": "A cinematic night scene on a remote volcanic shoreline transformed into a futuristic tidepool observatory. The camera begins low over black wet rocks as luminous turquoise tide pools pulse like living constellations. Transparent instruments, brass and glass research lanterns, and delicate weather vanes catch the moonlight. In the middle distance, a lone researcher in a weatherproof ivory coat kneels beside a glowing pool while tiny crab-like survey robots leave elegant trails in the sand. A slow forward dolly reveals bioluminescent foam rolling in with each wave, reflections shimmering across polished stone. Overhead, a vast indigo sky with dense stars and a faint green aurora. The surf produces rhythmic motion, soft mist drifts through the frame, and the observatory lights respond subtly to the changing tide. Rich ambient audio: layered ocean waves, crystalline water drips, distant wind through metal chimes, gentle electronic monitoring tones, and a low atmospheric hum. Ultra-detailed, photoreal cinematic lighting, smooth temporal coherence, moody high-end science fantasy production design.",
  "negativePrompt": "blurry, low detail, jittery motion, flicker, duplicate subjects, distorted anatomy, cartoon, text, watermark, logo, harsh overexposure, noisy audio, broken objects, chaotic camera shake",
  "width": 1280,
  "height": 704,
  "duration": 8,
  "fps": 24,
  "steps": 40,
  "CFGScale": 4,
  "settings": {
    "enhancePrompt": true
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "4d89f0f5-1277-48ee-875d-58e07a4b09d3",
  "videoUUID": "33c3f183-8546-4c85-8a15-1faab1c8422e",
  "videoURL": "https://vm.runware.ai/video/os/a23d05/ws/5/vi/33c3f183-8546-4c85-8a15-1faab1c8422e.mp4",
  "seed": 1461610484,
  "cost": 0.24
}

Image to Video

Bioluminescent Mangrove Night Voyage

Request

{
  "taskType": "videoInference",
  "taskUUID": "5282121f-0c07-45f9-8aa4-0563195f89df",
  "model": "lightricks:ltx@2",
  "positivePrompt": "Using the provided first frame as the opening shot, create a cinematic night sequence moving gently forward through luminous mangrove channels. The boat continues drifting through glowing water while mist curls between the roots, tiny bioluminescent insects swirl in layered depth, and distant lantern lights shimmer through the fog. Preserve the framing, subject identity, cloak color, and overall composition of the first frame, then add subtle natural motion: water ripples, soft branch sway, drifting spores, faint reflections, and a gradual reveal of a wider hidden lagoon. Moody, immersive, realistic, poetic, high temporal coherence, elegant camera movement, audiovisual storytelling atmosphere.",
  "negativePrompt": "flicker, jitter, warped anatomy, extra limbs, sudden camera cuts, chaotic motion, oversaturated colors, text, watermark, logo, low detail, blurry subject, duplicated objects, deformed boat, daytime lighting, cartoon style",
  "width": 1536,
  "height": 896,
  "duration": 8,
  "fps": 24,
  "steps": 40,
  "CFGScale": 4.5,
  "settings": {
    "enhancePrompt": true
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/edc95535-9838-4f1d-88ee-15a7dd1f7cc6.jpg",
        "frame": "first"
      }
    ]
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "5282121f-0c07-45f9-8aa4-0563195f89df",
  "videoUUID": "f77c26ca-e53f-47f5-9943-c8cd18b83de7",
  "videoURL": "https://vm.runware.ai/video/os/a25d05/ws/5/vi/f77c26ca-e53f-47f5-9943-c8cd18b83de7.mp4",
  "seed": 1358884006,
  "cost": 0.24
}

Text to Video

Bioluminescent Mangrove Lagoon Nocturne

Request

{
  "taskType": "videoInference",
  "taskUUID": "2ac0f7a3-e508-45dc-87a1-412fb1430e3b",
  "model": "lightricks:ltx@2",
  "positivePrompt": "A cinematic night voyage through a bioluminescent mangrove lagoon under a crescent moon, low camera gliding just above dark glassy water between twisted roots and arching branches. Electric-blue plankton shimmer in the wake, amber fireflies pulse among hanging vines, translucent jellyfish-like spores drift through humid air, and tiny tree frogs chirp from the shadows. A narrow wooden canoe with woven lanterns passes slowly in the midground, carrying a cloaked botanist with reflective instruments and specimen jars. Gentle ripples, subtle leaf movement, curling mist, moonbeams filtering through the canopy, luminous fish darting beneath the surface, distant thunderclouds on the horizon. Natural, immersive synchronized audio: water lapping, insects, frogs, soft wood creaks, faint wind, occasional distant thunder, delicate crystalline chimes from the glowing spores. Ultra-detailed, dreamlike realism, smooth temporal coherence, moody teal-and-amber palette, cinematic depth, atmospheric volumetric lighting.",
  "negativePrompt": "low resolution, flicker, jitter, duplicated subjects, deformed canoe, extra limbs, text, watermark, logo, overexposed highlights, harsh camera shake, cartoon style, flat lighting, noisy audio, distorted sound",
  "width": 1280,
  "height": 768,
  "duration": 8,
  "fps": 24,
  "steps": 40,
  "CFGScale": 4,
  "settings": {
    "enhancePrompt": true
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "2ac0f7a3-e508-45dc-87a1-412fb1430e3b",
  "videoUUID": "3d4059c9-e4b6-41b8-b22c-f49fefb3d02d",
  "videoURL": "https://vm.runware.ai/video/os/a23d05/ws/5/vi/3d4059c9-e4b6-41b8-b22c-f49fefb3d02d.mp4",
  "seed": 561683367,
  "cost": 0.24
}