# Ltx 2.3 Quality Extend Video — Atlas Cloud API

> Generate high-quality video with audio from images using LTX-2.3

This is the machine-readable API reference for **Ltx 2.3 Quality Extend Video** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `ltx-2.3-quality/extend-video`
- **Built by**: LIGHTRICKS
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/ltx-2.3-quality/extend-video
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.002 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "ltx-2.3-quality/extend-video"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video ltx-2.3-quality/extend-video -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `ltx-2.3-quality/extend-video`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"ltx-2.3-quality/extend-video"`

- **`prompt`** (`string`, _required_):
  Text description of the extended scene. Maximum 2,000 characters.
  - Default: `"Continue the scene naturally, maintaining the same style, lighting, and motion dynamics"`

- **`video_url`** (`string`, _required_):
  URL of the input video to extend. Supported formats: mp4, mov, webm, m4v, gif.

- **`extend_direction`** (`string`, _optional_):
  Direction in which to extend the video.
  - Default: `"forward"`
  - Options: "forward", "backward"

- **`num_frames`** (`integer`, _optional_):
  Number of frames to generate for the extension. Must be a multiple of 8 plus 1 (e.g. 25, 41, 81, 121).
  - Default: `81`
  - Min: 9
  - Max: 481

- **`resolution`** (`string`, _optional_):
  Output video resolution preset.
  - Default: `"landscape_16_9"`
  - Options: "square_hd", "square", "portrait_3_4", "portrait_9_16", "landscape_4_3", "landscape_16_9"

- **`match_input_fps`** (`boolean`, _optional_):
  Whether to match the frame rate of the source video.
  - Default: `true`

- **`generate_audio`** (`boolean`, _optional_):
  Whether to generate accompanying audio for the extended video.
  - Default: `false`

- **`seed`** (`integer`, _optional_):
  Random seed for reproducibility. Use the same seed and prompt to reproduce results.
  - Min: 0



**Required Parameters Example**:

```json
{
  "model": "ltx-2.3-quality/extend-video",
  "prompt": "Continue the scene naturally, maintaining the same style, lighting, and motion dynamics",
  "video_url": ""
}
```


**Full Example**:

```json
{
  "model": "ltx-2.3-quality/extend-video",
  "prompt": "Continue the scene naturally, maintaining the same style, lighting, and motion dynamics",
  "video_url": "",
  "extend_direction": "forward",
  "num_frames": 81,
  "resolution": "landscape_16_9",
  "match_input_fps": true,
  "generate_audio": false,
  "seed": 0
}
```


### Output Schema

The API returns the following output format:


- **`model`** (`string`, _optional_):
  model name
  - Default: `"ltx-2.3-quality/extend-video"`

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z").

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated videos. Null when status is not completed.

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "model": "ltx-2.3-quality/extend-video",
  "created_at": "",
  "id": "",
  "outputs": [
    ""
  ],
  "status": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ltx-2.3-quality/extend-video",
  "prompt": "Continue the scene naturally, maintaining the same style, lighting, and motion dynamics",
  "video_url": "",
  "extend_direction": "forward",
  "num_frames": 81,
  "resolution": "landscape_16_9",
  "match_input_fps": true,
  "generate_audio": false,
  "seed": 0
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/ltx-2.3-quality/extend-video)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### LTX 2.3 Quality Extend Video

**LTX 2.3 Quality Extend Video** seamlessly extends an existing video forward or backward, generating new frames that match the source video's style, lighting, and motion dynamics. Only the generated extension is billed — source frames are never charged.

#### 🌟 Key Features

##### ⏩ Bidirectional Extension
Extend a video forward to continue the scene, or backward to generate a natural-looking prequel — all from the same model.

##### 🎨 Style-Consistent Generation
The model analyzes the source video's visual style, color grading, and motion patterns, producing extensions that blend seamlessly with the original.

##### 🎞 Frame Rate Matching
Optionally match the source video's frame rate for a perfectly smooth, artifact-free result.

##### 🔊 Optional Audio Generation
Optionally generate audio for the extended segment.

##### 🔁 Reproducible Results
Pin a seed value to reproduce or iterate on a specific generation.

#### ⚙️ Parameters

| Parameter | Required | Description |
|---|---|---|
| `prompt` | ✅ | Text description of the extended scene. Maximum 2,000 characters. |
| `video_url` | ✅ | URL of the input video to extend. Supported: mp4, mov, webm, m4v, gif. |
| `extend_direction` | ❌ | Direction of extension: `forward` (default) or `backward`. |
| `num_frames` | ❌ | Number of frames to generate for the extension (default: `81`). |
| `resolution` | ❌ | Output video resolution preset (default: `landscape_16_9`). See options below. |
| `match_input_fps` | ❌ | Whether to match the source video's frame rate (default: `true`). |
| `generate_audio` | ❌ | Whether to generate accompanying audio (default: `false`). |
| `seed` | ❌ | Random seed for reproducibility. Omit for random results. |

##### Resolution Options

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/ltx-2.3-quality/extend-video · Docs: https://www.atlascloud.ai/docs