# Luma Ray 3.2 Reframe

> Reframe a video to a new aspect ratio using Luma Ray 3.2 (early access).

## Overview

- **Model ID**: `luma-ray-3.2-reframe-video`
- **Workflow**: `luma-ray32-video-reframe`
- **Provider**: Luma
- **Origin**: Partner Model
- **Category**: Video → Video (video)
- **Output**: A video URL.
- **Tags**: video input, reframe
- **Unified endpoint**: `POST https://api.picsart.com/workflows/v1/models/execute` (model id in the body)
- **Compatibility endpoint**: `POST https://api.picsart.com/workflows/luma-ray32-video-reframe/execute` (vendor's own parameters)
- **Execution**: long-running — use the async submit/poll pair or the SDK, which polls for you
- **Model page**: https://picsart.com/api-platform/models/luma-ray-3.2-reframe-video

## Pricing

Rates are in USD. Every row below is an exact rate for the settings it names — the columns are the settings that change the price for this model. Every response reports what was actually charged in `response.usage.credits`.

| Tier | Use case | Rate |
| --- | --- | --- |
| Standard 540p | Image → video | $0.033 / sec |
| Reframe 540p | Video → video | $0.066 / sec |
| Standard 720p | Image → video | $0.066 / sec |
| Standard 540p | Text → video | $0.10 / sec |
| Reframe 720p | Video → video | $0.12 / sec |
| Standard 540p | Video → video | $0.1584 / sec |
| Standard 720p | Text → video | $0.20 / sec |
| Standard 720p | Video → video | $0.2376 / sec |
| HDR 720p, Standard 1080p | Image → video | $0.264 / sec |
| HDR 720p | Text → video | $0.264 / sec |
| Reframe 1080p | Video → video | $0.36 / sec |
| Standard 1080p | Text → video | $0.40 / sec |
| HDR EXR 720p | Image → video, Text → video | $0.462 / sec |
| HDR 720p, Standard 1080p | Video → video | $0.4752 / sec |
| HDR EXR 720p | Video → video | $0.8316 / sec |
| HDR 1080p | Video → video | $0.9504 / sec |
| HDR 1080p | Image → video, Text → video | $1.056 / sec |
| HDR EXR 1080p | Video → video | $1.664 / sec |
| HDR EXR 1080p | Image → video, Text → video | $1.848 / sec |

Published rates. Volume pricing, invoicing and annual agreements: https://picsart.com/api-platform/contact-sales

## Authentication

The SDK and the REST API authenticate with a Picsart API key sent as a bearer token. Create a key in the console at https://picsart.com/api-platform/dashboard/api-keys, keep it in a server-side environment variable, and never ship it in browser code or commit it.

```bash
export PICSART_API_KEY="YOUR_KEY"
```

```http
Authorization: Bearer $PICSART_API_KEY
```

The CLI and the MCP server do not use an API key: `gen-ai login` signs in through the browser once per machine and stores a token locally.

## Interfaces

- **SDK (TypeScript)** — `@picsart/ai-sdk` (Node 20+, ESM). Type-safe `ai.generate()` / `ai.generateText()` with per-model parameter types; polls long jobs for you.
- **SDK (Python)** — `picsart-ai-sdk` (Python 3.10+, async). The same surface in snake_case: `await ai.generate()` / `await ai.generate_text()`, with a typed input per model.
- **REST** — the API gateway at `https://api.picsart.com`. Sync `/execute`, or async `/submit` + `/{taskId}/result`.
- **CLI** — `@picsart/gen-ai` (`gen-ai`). Generate from a terminal, quote cost before spending, emit JSON for pipelines.
- **MCP** — the same models inside Claude Code, Cursor, Windsurf and other MCP hosts. Setup: https://picsart.com/gen-ai-mcp/

```bash
npm install @picsart/ai-sdk      # SDK (TypeScript)
pip install picsart-ai-sdk       # SDK (Python)
npm install -g @picsart/gen-ai   # CLI (also drives the MCP server)
```

## Unified API (recommended)

One parameter set, used by the SDK and by REST alike: the names below are what `ai.generate('luma-ray-3.2-reframe-video', …)` takes, and what goes inside the inner `params` of a REST call. Over REST the model id travels in the body, not the path — one workflow, `v1/models`, fronts the whole catalogue.

### Execution modes

- **Sync** — `POST /workflows/v1/models/execute` returns the result in one call. Only for jobs that finish within ~20 seconds; otherwise it times out.
- **Async** — `POST /workflows/v1/models/submit` returns a task id; poll `GET /workflows/v1/models/{taskId}/result` until `response.status` is `COMPLETED` or `FAILED`. Task statuses: `ACCEPTED` · `IN_PROGRESS` · `COMPLETED` · `FAILED`.
- **SDK** — `ai.generate()` always awaits the finished result; polling is hidden.

Video jobs routinely outrun the sync limit: use async over REST, or the SDK, which polls for you.

### Input parameters

- **`prompt`** (`string`, _required_): What to make, in plain language: the subject, style, composition and motion. With an input image or video, what to change.
  - Max length: 5000 characters
- **`aspectRatio`** (`string`, _optional_): Shape of the output as width:height. An auto or adaptive option follows the input image.
  - Default: `"16:9"`
  - Options: `9:16`, `3:4`, `1:1`, `4:3`, `16:9`, `21:9`
- **`videoUrl`** (`string`, _required_): The video to work on, as a URL.
  - Accepts: video URL, up to 30s
- **`resolution`** (`string`, _optional_): Output size. Higher costs more and takes longer.
  - Default: `"720p"`
  - Options: `540p`, `720p`, `1080p`

### Input JSON Schema

The inner `params` object. Over REST it is wrapped as `{ "params": { "model": "<id>", "params": <this> } }`; the SDK takes it directly.

```json
{
  "type": "object",
  "required": [
    "prompt",
    "videoUrl"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "maxLength": 5000,
      "description": "What to make, in plain language: the subject, style, composition and motion. With an input image or video, what to change."
    },
    "aspectRatio": {
      "type": "string",
      "enum": [
        "9:16",
        "3:4",
        "1:1",
        "4:3",
        "16:9",
        "21:9"
      ],
      "default": "16:9",
      "description": "Shape of the output as width:height. An auto or adaptive option follows the input image."
    },
    "videoUrl": {
      "type": "string",
      "format": "uri",
      "description": "The video to work on, as a URL."
    },
    "resolution": {
      "type": "string",
      "enum": [
        "540p",
        "720p",
        "1080p"
      ],
      "default": "720p",
      "description": "Output size. Higher costs more and takes longer."
    }
  },
  "additionalProperties": false
}
```

### Required parameters example

The required parameters plus the defaults that shape the output, as a REST body:

```json
{
  "params": {
    "model": "luma-ray-3.2-reframe-video",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "aspectRatio": "16:9",
      "videoUrl": "https://cdn.example.com/input.mp4",
      "resolution": "720p"
    }
  }
}
```

### Response

The body is the gateway's status envelope: the output is at `response.result`, next to the task id, its status and the credits charged. Asset models return `url` plus an `items` array of results.

```json
{
  "status": "success",
  "response": {
    "id": "task_abc123",
    "status": "COMPLETED",
    "result": {
      "url": "https://cdn.picsart.com/…/result",
      "items": [
        {
          "url": "https://cdn.picsart.com/…/result"
        }
      ],
      "model": "luma-ray-3.2-reframe-video"
    }
  }
}
```

What `ai.generate()` / `ai.generateText()` resolve to (the envelope already unwrapped):

```json
{
  "items": [
    {
      "url": "https://cdn.picsart.com/…/result"
    }
  ],
  "model": "luma-ray-3.2-reframe-video"
}
```

### Usage examples

#### TypeScript (SDK)

```typescript
import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

const result = await ai.generate('luma-ray-3.2-reframe-video', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  aspectRatio: "16:9",
  videoUrl: "https://cdn.example.com/input.mp4",
  resolution: "720p"
});

console.log(result.url); // video URL
```

#### Python (SDK)

```python
import asyncio
import os

from picsart_ai_sdk import create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        result = await ai.generate("luma-ray-3.2-reframe-video", {
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
            "aspectRatio": "16:9",
            "videoUrl": "https://cdn.example.com/input.mp4",
            "resolution": "720p",
        })

        print(result.url)  # video URL


asyncio.run(main())
```

#### cURL (sync)

```bash
curl -X POST 'https://api.picsart.com/workflows/v1/models/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "luma-ray-3.2-reframe-video",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "aspectRatio": "16:9",
      "videoUrl": "https://cdn.example.com/input.mp4",
      "resolution": "720p"
    }
  }
}'
```

#### cURL (async: submit, then poll)

```bash
# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/v1/models/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "luma-ray-3.2-reframe-video",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "aspectRatio": "16:9",
      "videoUrl": "https://cdn.example.com/input.mp4",
      "resolution": "720p"
    }
  }
}'
# → { "status": "success", "response": { "id": "task_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/v1/models/task_abc123/result' \
  -H 'Authorization: Bearer $PICSART_API_KEY'
```

#### CLI

```bash
gen-ai login  # once per machine
gen-ai models info luma-ray-3.2-reframe-video  # this model's parameters
gen-ai pricing luma-ray-3.2-reframe-video  # quote before spending credits
gen-ai generate -m luma-ray-3.2-reframe-video \
  -p "A serene mountain lake at golden hour" \
  --ar 16:9
```

## Compatibility API (vendor parameters)

Alongside the unified API, the `luma-ray32-video-reframe` workflow takes Luma's own parameters exactly as the vendor defines them — nothing renamed or reshaped. It is the shortest path onto Picsart for request bodies already written against the vendor; the trade is that a request is written for one vendor, and the result comes back in the vendor's own shape. Same authentication.

- **Endpoint**: `POST https://api.picsart.com/workflows/luma-ray32-video-reframe/execute` (sync) · `POST …/submit` + `GET …/{taskId}/result` (async)
- **SDK**: `ai.apis.run('luma-ray32-video-reframe', params, { mode })` in TypeScript, `ai.apis.run("luma-ray32-video-reframe", params, mode=…)` in Python — params forwarded verbatim

### Vendor parameters

| Parameter | Type | Required | Default | Details |
| --- | --- | --- | --- | --- |
| `prompt` | `string` | yes | — | Describes the content to paint into the new canvas area (1-6000 characters) |
| `aspect_ratio` | `string` | yes | — | Target aspect ratio (must differ from the source). · Options: `9:16`, `3:4`, `1:1`, `4:3`, `16:9`, `21:9` |
| `source` | `object` | yes | — | Source video: generation_id, or url/data with video/* media_type (≤30s). |
| └ `generation_id` | `string` | no | — | Chain reference to a prior completed video generation owned by the same client |
| └ `url` | `string` | no | — | Partner-hosted video URL. Requires media_type (video/*). Source must be ≤ 30s. |
| └ `data` | `string` | no | — | Inline base64 video. Requires media_type (video/*). Source must be ≤ 30s. |
| └ `media_type` | `string` | no | — | Video MIME type when url/data is used (e.g. "video/mp4") |
| `user_id` | `string` | no | — | Stable opaque end-user identifier (no PII), ≤256 chars. |
| `video` | `object` | no | — | Video output + reframe options. Standard dynamic range only — HDR/EXR, loop, edit, and anchor frames are not applicable to reframe. |
| └ `resolution` | `string` | no | — | Output resolution. · Options: `540p`, `720p`, `1080p` |
| └ `source_position` | `object` | no | — | Normalized rect controlling where the source sits in the new canvas. Omit for centered-fit. |
| └   `x_norm` | `number` | yes | — | Left edge of source rect, fraction of canvas width [-2.0, 2.0] |
| └   `y_norm` | `number` | yes | — | Top edge of source rect, fraction of canvas height [-2.0, 2.0] |
| └   `w_norm` | `number` | yes | — | Source rect width, fraction of canvas width (0, 2.0] |
| └   `h_norm` | `number` | yes | — | Source rect height, fraction of canvas height (0, 2.0] |
| `options` | `object` | no | — | GenAI options (safety checks, Picsart Drive) |
| └ `safety_checks` | `object` | no | — | Safety check settings |
| └   `enabled` | `boolean` | no | — | Whether to run content moderation. Defaults to true. |
| └ `drive` | `object` | no | — | Save result to Picsart Drive |
| └   `name` | `string` | yes | — | File name in Picsart Drive |
| └   `attributes` | `object` | no | — | Custom attributes to attach to the file |
| └   `folder` | `object` | no | — | Target folder in Picsart Drive |
| └ `inputs_transformation` | `object` | no | — | Input transformation settings |
| └   `downscale_oversized_images` | `boolean` | no | — | Whether to downscale oversized input images. Defaults to false. |

### Example request body

```json
{
  "params": {
    "prompt": "A serene mountain lake at golden hour, ultra detailed",
    "aspect_ratio": "9:16",
    "source": {}
  }
}
```

### Usage examples

#### TypeScript (`ai.apis.run`)

```typescript
import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// Calls the 'luma-ray32-video-reframe' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('luma-ray32-video-reframe', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  aspect_ratio: "9:16",
  source: {}
}, {
  mode: ApiRunMode.SYNC,
});

console.log(result); // workflow-specific output
console.log(usage?.credits); // amount charged, in $
```

#### Python (`ai.apis.run`)

```python
import asyncio
import os

from picsart_ai_sdk import ApiRunMode, create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        # Calls the 'luma-ray32-video-reframe' workflow directly — params are sent as-is.
        response = await ai.apis.run("luma-ray32-video-reframe", {
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
            "aspect_ratio": "9:16",
            "source": {},
        }, mode=ApiRunMode.SYNC)

        print(response["result"])  # workflow-specific output
        print((response.get("usage") or {}).get("credits"))  # amount charged, in $


asyncio.run(main())
```

#### cURL (sync)

```bash
curl -X POST 'https://api.picsart.com/workflows/luma-ray32-video-reframe/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "prompt": "A serene mountain lake at golden hour, ultra detailed",
    "aspect_ratio": "9:16",
    "source": {}
  }
}'
```

#### cURL (async: submit, then poll)

```bash
# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/luma-ray32-video-reframe/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "prompt": "A serene mountain lake at golden hour, ultra detailed",
    "aspect_ratio": "9:16",
    "source": {}
  }
}'
# → { "status": "success", "response": { "id": "wf_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/luma-ray32-video-reframe/wf_abc123/result' \
  -H 'Authorization: Bearer $PICSART_API_KEY'
```

### Response

Over HTTP the vendor-shaped result arrives inside the gateway envelope at `response.result`:

```json
{
  "status": "success",
  "response": {
    "id": "wf_abc123",
    "status": "COMPLETED",
    "result": {
      "url": "https://cdn.picsart.com/…/result.mp4",
      "mimeType": "video/mp4",
      "driveFile": {
        "id": "wf_abc123"
      }
    }
  }
}
```

`ai.apis.run()` unwraps that envelope and resolves to `{ result, usage }`:

```json
{
  "result": {
    "url": "https://cdn.picsart.com/…/result.mp4",
    "mimeType": "video/mp4",
    "driveFile": {
      "id": "wf_abc123"
    }
  }
}
```

## Additional resources

- Model page (playground): https://picsart.com/api-platform/models/luma-ray-3.2-reframe-video
- SDK and REST API (unified): https://picsart.com/api-platform/models/luma-ray-3.2-reframe-video#api
- Compatibility API (vendor parameters): https://picsart.com/api-platform/models/luma-ray-3.2-reframe-video#advanced
- Pricing: https://picsart.com/api-platform/models/luma-ray-3.2-reframe-video#pricing
- This document: https://picsart.com/api-platform/models/luma-ray-3.2-reframe-video/llms.txt
- All models: https://picsart.com/api-platform/models
- Docs — quickstart https://picsart.com/api-platform/docs/quickstart, authentication https://picsart.com/api-platform/docs/authentication, SDK https://picsart.com/api-platform/docs/sdk, REST https://picsart.com/api-platform/docs/api-reference, CLI https://picsart.com/api-platform/docs/cli, MCP https://picsart.com/api-platform/docs/mcp
- CLI reference: https://picsart.github.io/picsart-mcp-cli-docs/guide/introduction