MODEL ID lightricks:3@1

live

LTX-2 Retake

by Lightricks November 28, 2025

LTX-2 Retake regenerates targeted segments inside an existing clip. Define start time and duration. Replace video, audio or both with new prompts. Preserve surrounding motion and continuity. Ideal for selective revisions, dialog tweaks, and shot refinements without full regen.

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).

inputs » video video string required: Video input (UUID or URL).

Generation Parameters

Core parameters for controlling the generated content.

model string required value: lightricks:3@1

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string min: 1 max: 5000

Text prompt describing elements to include in the generated output.

Learn more 2 resources

Provider Settings

Parameters specific to this model provider. These must be nested inside the providerSettings.lightricks object.

providerSettings » lightricks » duration duration integer min: 1: Duration in seconds to regenerate. Combined with startTime must not exceed input video length.

providerSettings » lightricks » mode mode string default: replace_audio_and_video

Track replacement mode for the edited segment.

Allowed values 3 values

: Regenerate only the audio track, preserving original video.
: Regenerate only the video track, preserving original audio.
: Regenerate both audio and video tracks.

providerSettings » lightricks » startTime startTime integer min: 0: Start time in seconds for the regenerated segment. Must be within input video duration.

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.

Video to Video

Windblown Salt Flats Chase

Request

{
  "taskType": "videoInference",
  "taskUUID": "2eb310fd-c023-46a5-a0fa-5e977ff54bce",
  "model": "lightricks:3@1",
  "positivePrompt": "Replace the selected segment with a more dramatic continuation of the salt-flat motorcycle chase: one rider cuts sharply across the other leaving a sweeping ribbon of dust, the camera drops lower near the ground for a fast tracking angle, tires scatter crystalline grit, distant mountains shimmer in the heat haze, naturalistic cinematic motion, realistic sunlight, seamless match to the surrounding footage. Regenerate both sound and picture with roaring engines, skidding grit, rushing wind, and a brief tense near-collision feeling.",
  "providerSettings": {
    "lightricks": {
      "startTime": 2,
      "duration": 3,
      "mode": "replace_audio_and_video"
    }
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/dfaf49f6-a1d2-4f75-b705-7f9fc11614ef.mp4"
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "2eb310fd-c023-46a5-a0fa-5e977ff54bce",
  "videoUUID": "eb3d2591-8f26-4c24-9b6b-cb72d1f8d84c",
  "videoURL": "https://vm.runware.ai/video/os/a04d20/ws/5/vi/eb3d2591-8f26-4c24-9b6b-cb72d1f8d84c.mp4",
  "cost": 0.605
}

Video to Video

Hailstorm Rooftop Violin Solo

Request

{
  "taskType": "videoInference",
  "taskUUID": "fd711854-7776-4ba6-aabc-45346fc7ec37",
  "model": "lightricks:3@1",
  "positivePrompt": "Retake only the selected segment so the rooftop performance suddenly shifts into a violent hailstorm. Keep the same violinist, wardrobe, camera angle, framing, rooftop layout, skyline placement, and motion continuity from the surrounding clip. Dark gust clouds roll in fast, loose sheets snap on a clothesline, hailstones ricochet across puddles and concrete, the musician braces against the wind while continuing to play with intense concentration. Cinematic realism, wet surfaces, sharp atmospheric detail, natural motion blur, believable continuity at the edit boundaries. Replace audio and video with fierce wind, rattling hail impacts, fluttering fabric, distant thunder, and a more forceful, urgent violin phrase that matches the performer’s movements.",
  "providerSettings": {
    "lightricks": {
      "startTime": 2,
      "duration": 3,
      "mode": "replace_audio_and_video"
    }
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/a5fa4c72-d8d2-48e7-bbe7-69107238ef47.mp4"
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "fd711854-7776-4ba6-aabc-45346fc7ec37",
  "videoUUID": "cb6f3ad7-5c1d-436c-8bf7-5a05ba1284cc",
  "videoURL": "https://vm.runware.ai/video/os/a15d18/ws/5/vi/cb6f3ad7-5c1d-436c-8bf7-5a05ba1284cc.mp4",
  "cost": 0.605
}

Video to Video

Fogbound Viaduct Train Crossing

Request

{
  "taskType": "videoInference",
  "taskUUID": "b049395b-2798-47d4-a238-06ada89c143b",
  "model": "lightricks:3@1",
  "positivePrompt": "For the selected segment, transform the outside view into a surreal yet believable encounter: a giant manta-shaped wind craft made of ribbed canvas and polished brass glides alongside the train at close distance, its wings flexing in the mist, droplets trailing from the frame, soft amber guide lamps glowing under its body, swirling fog displaced by its passage, realistic motion parallax from the train window, cinematic atmosphere, seamless continuity with the original shot, matching camera angle and movement; regenerate sound to include deep fabric creaks, gusting air, resonant cable hum, and a brief hush from awestruck passengers while keeping the train ambience coherent.",
  "providerSettings": {
    "lightricks": {
      "startTime": 2,
      "duration": 3,
      "mode": "replace_audio_and_video"
    }
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/a3978086-ee43-4a4a-b9ee-f4462cfdd7d0.mp4"
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "b049395b-2798-47d4-a238-06ada89c143b",
  "videoUUID": "aa18d70a-418e-4789-8870-a160df40c151",
  "videoURL": "https://vm.runware.ai/video/os/a05d22/ws/5/vi/aa18d70a-418e-4789-8870-a160df40c151.mp4",
  "cost": 0.605
}

Video to Video

Subterranean Crystal Tram Arrival

Request

{
  "taskType": "videoInference",
  "taskUUID": "1cf591e2-05cd-46b6-988d-4b3b8daacdcf",
  "model": "lightricks:3@1",
  "positivePrompt": "Transform the selected segment into a majestic underground transit stop carved through towering quartz and copper-veined stone, with a sleek glass-sided tram gliding in on polished tracks. Shimmering crystals embedded in the cavern walls cast soft prismatic highlights across the platform. A few travelers in weathered expedition coats wait calmly with satchels and instrument cases. Fine dust motes drift in the air, subtle reflections ripple across the tram windows, and the arrival soundscape becomes a resonant metallic hum with echoing rail friction and distant cavern ambience. Keep camera movement, timing, and scene continuity natural with the surrounding clip.",
  "providerSettings": {
    "lightricks": {
      "startTime": 2,
      "duration": 3,
      "mode": "replace_audio_and_video"
    }
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/8645e38e-d263-4976-a5a0-344f1da81cab.mp4"
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "1cf591e2-05cd-46b6-988d-4b3b8daacdcf",
  "videoUUID": "94936a61-18fa-4f13-8826-254f811ca441",
  "videoURL": "https://vm.runware.ai/video/os/a12d13/ws/5/vi/94936a61-18fa-4f13-8826-254f811ca441.mp4",
  "cost": 0.605
}