---
title: LTX-2.3 Fast | Runware Docs
url: https://runware.ai/docs/models/lightricks-ltx-2-3-fast
description: Fast multimodal video generation optimized for rapid iteration
---
# LTX-2.3 Fast

![LTX-2.3 Fast](https://assets.runware.ai/covers/lightricks-ltx-2-3-fast.jpg)

LTX-2.3 Fast is a performance-optimized variant of LTX 2.3 designed for rapid video generation with synchronized audio. It supports text-to-video, image-to-video, and audio-conditioned workflows while prioritizing speed, responsiveness, and cost efficiency for draft, preview, and high-velocity creative production use cases.

- **Status**: live
- **ID**: `lightricks:ltx@2.3-fast`
- Try in Playground
- **Creator**: Lightricks
- **Release Date**: March 5, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Video, Image to Video, Audio to Video, Checkpoint, Audio

## Pricing

$0.03 from, per second · ~46s per request

**Rates** (per second)

- 720p: `$0.03`
- 1080p: `$0.06`
- 2K: `$0.12`

**5 example generations**

- [first-last-frame](https://runware.ai/docs/models/lightricks-ltx-2-3-fast/examples#example-couture-beekeeping-suit-showcase) · 1280×768 · 8s: `$0.48` (~33s)
- [text-to-video](https://runware.ai/docs/models/lightricks-ltx-2-3-fast/examples#example-seaweed-biotech-logo-ident) · 1080p · 5s: `$0.60` (~52s)
- [multiple-keyframes](https://runware.ai/docs/models/lightricks-ltx-2-3-fast/examples#example-rare-book-rescue-presenter-clip) · 1536×896 · 10s: `$0.60` (~46s)
- [first-frame](https://runware.ai/docs/models/lightricks-ltx-2-3-fast/examples#example-wildfire-atlas-logo-motion-loop) · 1080p · 6s: `$0.72` (~53s)
- [audio-driven](https://runware.ai/docs/models/lightricks-ltx-2-3-fast/examples#example-oyster-hatchery-biosecurity-presenter-clip) · 1024×1024 · 12s: `$0.72` (~43s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

`width` and `height` must be used together.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

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

### [outputType](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-outputformat)

- **Type**: `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**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses 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](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-uploadendpoint)

- **Type**: `string`
- **Format**: `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.

```text
// 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](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-numberresults)

- **Type**: `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.

### [frameImages](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `10`

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 position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. 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.
- **2 images**: First and last frames.
- **3+ images**: First and last frames, with intermediate images evenly spaced between.

**Examples**:

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

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

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

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

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Multiple frames:** With three or more images, the first and last are anchored while intermediate frames are evenly distributed across the timeline.

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  },
  "c00abf5f-6cdb-4642-a01d-1bfff7bc3cf7",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

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

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

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

#### [frame](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `string | integer`
- **Min**: `-1`

Target frame position for the image. Accepts a named position like `first` or `last`, or a zero-based frame index (-1 for the last frame).

**Allowed values**: `first` `last`

### [audio](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-inputs-audio)

- **Path**: `inputs.audio`
- **Type**: `string`
- **Duration**: `up to 30s`

Audio input (UUID or URL). Enables audio-to-video conditioning. The audio is merged with the generated video and trimmed to fit the video duration. Maximum duration 30 seconds.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `lightricks:ltx@2.3-fast`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `10000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-width)

- **Type**: `integer`
- **Required**: true
- **Min**: `128`
- **Max**: `2048`
- **Step**: `64`

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `128`
- **Max**: `2048`
- **Step**: `64`

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [duration](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-duration)

- **Type**: `float`
- **Required**: true
- **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](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-fps)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `120`
- **Default**: `25`

Frames per second for video generation. Higher values create smoother motion but require more processing time.

### [seed](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `9223372036854776000`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Learn more** (1 resource):

- [Seed](https://runware.ai/docs/learn/seed) (learn)

### [lora](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-lora)

- **Path**: `lora.model`
- **Type**: `array of objects (3 properties)`
- **Min items**: `1`

With LoRA (Low-Rank Adaptation), you can adapt a model to specific styles or features by emphasizing particular aspects of the data. This technique enhances the quality and relevance of generated content and can be especially useful when the output needs to adhere to a specific artistic style or follow particular guidelines.

Multiple LoRA models can be used simultaneously to achieve different adaptation goals.

**Examples**:

```json
"lora": [
  {
    "model": "<lora-model-air>",
    "weight": 0.8
  }
]
```

**Learn more** (1 resource):

- [Loras](https://runware.ai/docs/learn/loras) (learn)

#### [model](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-lora-model)

- **Path**: `lora.model`
- **Type**: `string`
- **Required**: true

LoRA model identifier.

#### [weight](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-lora-weight)

- **Path**: `lora.weight`
- **Type**: `float`
- **Min**: `-4`
- **Max**: `4`
- **Step**: `0.01`
- **Default**: `1`

Strength of the LoRA influence. A value of 0 means no influence. Higher values increase the influence, and negative values can be used to steer away from the LoRA's style.

#### [transformer](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-lora-transformer)

- **Path**: `lora.transformer`
- **Type**: `string`
- **Default**: `both`

Transformer stages to apply LoRA. Some video models use separate high-noise and low-noise processing stages, and LoRAs can be selectively applied to optimize their effectiveness.

**Allowed values**:

- `high` Apply LoRA only to the high-noise processing stage (coarse structure and early generation steps).
- `low` Apply LoRA only to the low-noise processing stage (fine details and later generation steps).
- `both` Apply LoRA to both stages for full coverage.

**Settings**

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

### [enhancePrompt](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#request-settings-enhanceprompt)

- **Path**: `settings.enhancePrompt`
- **Type**: `boolean`
- **Default**: `true`

Enable automatic prompt enhancement for cinematic results.

## Response Parameters

### [taskType](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [seed](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/lightricks-ltx-2-3-fast#response-cost)

- **Type**: `float`

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

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/lightricks-ltx-2-3-fast/afaf6803-5ad8-471a-9544-29033411bcf2.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "1190930f-08a6-4aa9-a6c7-fafd6a9d204e",
  "model": "lightricks:ltx@2.3-fast",
  "positivePrompt": "Create a polished five-second cinematic logo ident for LITTORAL LABS, a seaweed-based biomaterials research company. Begin on a full-frame field of tactile midnight-blue paper with faint fibers visible. A thin copper line sweeps in from the lower left like an ink stroke, tracing two elegant mirrored kelp blades that unfurl and curl around each other to form a minimal circular emblem. Tiny salt-like particles lift from the paper as the mark completes, while soft underwater caustic light drifts slowly across the background. The emblem settles at center and the words “LITTORAL LABS” resolve beneath it in crisp, uppercase, widely tracked ivory sans-serif lettering; preserve this exact spelling and include no other text. Subject motion is graceful botanical unfurling with precise graphic-line animation; environmental motion is restrained drifting caustics and suspended particles. Camera begins in a straight-down macro view, makes a subtle controlled push toward the forming emblem, then locks perfectly centered for the final brand hold. Sophisticated editorial motion design, marine-science aesthetic, restrained palette of midnight blue, warm copper and bone ivory, premium natural texture, clean edges, strong legibility, no mockup or interface. Synchronized sound design: a soft paper brush, delicate watery shimmer and one warm glass chime as the logo locks into place; no speech or music.",
  "width": 1920,
  "height": 1088,
  "duration": 5
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/lightricks-ltx-2-3-fast/bfcdfde7-a353-4b86-b55e-31de9b3270d9.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "cc9b7ef3-1fd1-4756-943e-0272f807abbd",
  "model": "lightricks:ltx@2.3-fast",
  "positivePrompt": "Continue directly from the supplied first-frame logo artwork as a refined six-second seamless motion identity. Preserve the exact RIDGELINE FIRE ATLAS emblem, spelling, typography, proportions, centered portrait composition, ivory paper background, charcoal ink, and safety-orange accent throughout. Begin with the complete logo held still for a brief beat. The circular contour lines then animate organically along their existing paths like elevation data being plotted: successive charcoal rings travel outward with subtle hand-printed registration drift while the small orange map marker emits one restrained pulse. Fine orange route traces race around two contour arcs, then settle into the emblem. Add delicate tactile paper depth and barely perceptible ink grain movement without changing the clean flat-design character. Keep the wordmark stationary, sharp, and fully legible while the symbol moves. In the final second, all moving traces retract smoothly and the orange pulse fades, returning precisely to the supplied opening frame for a perfect loop. Locked camera, no zoom, no scene transition, no additional symbols or text. Subtle synchronized sound design: a soft paper rustle, quiet cartographic pencil ticks, and one muted low click on the orange pulse, resolving cleanly at the loop point.",
  "width": 1088,
  "height": 1920,
  "duration": 6,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/68bdab3b-8b4e-4f97-b361-498df638871e.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/lightricks-ltx-2-3-fast/2b63ea0c-85c5-4751-b761-1724eb1d0a27.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "1de6a5c7-1bbf-42be-9cc2-d21ef63ddf74",
  "model": "lightricks:ltx@2.3-fast",
  "positivePrompt": "Create a polished eight-second landscape fashion showcase reel connecting the supplied first and last frames in one continuous shot. Preserve the same model, ivory couture beekeeping suit, veil geometry, garment construction, courtyard and warm morning light throughout. Begin at the front-left three-quarter view. The camera makes a slow, precise clockwise orbit around the model at a constant distance, ending naturally at the supplied back-right three-quarter view. The model remains poised and nearly still, shifting her weight once and gently lowering one caramel-gloved hand so the tailored silhouette stays readable. A light breeze creates restrained movement in the veil mesh, pleated shoulders, dry grasses and loose canvas edges. Brief sunlight glances across the honey-gold seam tape and textured fabric as the camera passes the side profile. Premium sustainable workwear editorial art direction, elegant and tactile rather than rugged, chalky ivory, limestone, amber honey and muted black palette, crisp realistic materials, subtle depth of field, stable anatomy and consistent garment details. Seamless physical motion with no cuts, morphing, duplicated limbs, added accessories, logos, captions or on-screen text. Synchronized natural sound design: quiet linen rustle, soft courtyard breeze, distant restrained bee hum and one subtle leather glove creak.",
  "width": 1280,
  "height": 768,
  "duration": 8,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/70105daa-bd79-4be6-a579-2e2114fe5780.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/2dd89895-d8af-42da-b084-6c36d0a4299a.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

### multiple-keyframes (multiple-keyframes)

[Watch video](https://assets.runware.ai/examples/lightricks-ltx-2-3-fast/f1686514-140c-4381-84cc-f267c6452436.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "3ba13b43-77ee-4afe-8789-f97a7074eb53",
  "model": "lightricks:ltx@2.3-fast",
  "positivePrompt": "Create a polished ten-second talking-head safety training clip for library and museum staff. Maintain strict visual continuity through all three supplied keyframes: the same paper conservation laboratory, locked waist-up camera, soft window light, celadon walls, pale wood bench, archival shelves and muted cream, celadon and oxblood palette. The presenter is the same calm 58-year-old East Asian woman with a neat silver bob, oxblood conservation smock, cream collared shirt and pale nitrile gloves. She speaks directly to the viewer with natural facial movement, precise lip synchronization and a reassuring expert tone. Her gestures progress coherently: she begins beside the closed damp ledger, carefully blots its cover without opening it, slides it into the clear archival bag at the middle keyframe, seals the bag, then lowers it into the blue freezer crate by the final keyframe. Keep her upper body and face visible while she demonstrates. Spoken dialogue: “If a book gets soaked, don’t open it. Blot the cover, bag it, and freeze it within forty-eight hours to stop mold.” Realistic hand motion and object handling, subtle blinks and breathing, clean location dialogue with faint quiet laboratory room tone, no music, no camera movement, no cuts, no captions, no graphics, no logos.",
  "width": 1536,
  "height": 896,
  "duration": 10,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/ca329bc5-de96-456f-8682-1adf904ab35c.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/27013418-59b4-43d1-b500-b824147eea14.jpg",
        "frame": 125
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/c21f4bd9-5bf7-4f5a-8c90-cc91ffb15498.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

### audio-driven (audio-driven)

[Watch video](https://assets.runware.ai/examples/lightricks-ltx-2-3-fast/09de6b7f-8567-44a8-b0df-bcedc4b117e4.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "0224cf1f-3d2b-497a-b473-3cc9942d6894",
  "model": "lightricks:ltx@2.3-fast",
  "positivePrompt": "Create a polished 12-second talking-head training clip synchronized precisely to the supplied speech. A confident female marine pathologist in her early forties addresses the camera inside a modern oyster hatchery nursery. Chest-up square composition, centered with comfortable headroom. She wears clean sea-green waterproof overalls over a pale coral work shirt, with tied-back dark hair and no hat or face covering. Behind her, softly defocused turquoise cultivation tanks, white pipes, suspended hoses, and gentle water aeration establish a credible working shellfish facility without distracting from her face. Bright diffused daylight mixes with clean overhead industrial lighting for a fresh aqua, white, and coral palette. Her mouth movements accurately follow every word of the audio. She maintains reassuring eye contact and uses restrained, natural gestures timed to the instructions: a small downward gesture for rinsing boots, an open-hand gesture for sanitizing tools, and a subtle indication toward the tanks when mentioning logging visits. Her expression becomes slightly more earnest on the final sentence about protecting young oysters. Locked-off professional camera with a barely perceptible slow push-in, realistic facial motion, natural blinking, subtle breathing, accurate hands, documentary-style authenticity, crisp commercial training-video finish. One continuous take, no cuts, no captions, no logos, no on-screen text, no interface elements.",
  "width": 1024,
  "height": 1024,
  "duration": 12,
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/ce692887-ce17-4f11-802e-2ba01001d54d.mp3"
  }
}
```