# PixVerse V6 Fusion

> Fuse up to 7 reference images (subjects/backgrounds) into a new video scene with PixVerse V6.

## Overview

- **Model ID**: `pixverse-v6-fusion`
- **Workflow**: `pixverse/v2/reference-to-video`
- **Provider**: PixVerse
- **Origin**: Partner Model
- **Category**: Image → Video (video)
- **Output**: A video URL.
- **Tags**: reference images, audio, up to 1080p, 5-15 sec
- **Unified endpoint**: `POST https://api.picsart.com/workflows/v1/models/execute` (model id in the body)
- **Compatibility endpoint**: `POST https://api.picsart.com/workflows/pixverse/v2/reference-to-video/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/pixverse-v6-fusion

## Pricing

Live pricing for this model is not published yet. See https://picsart.com/pricing/ or the Pricing tab of the model page (https://picsart.com/api-platform/models/pixverse-v6-fusion#pricing).

## 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('pixverse-v6-fusion', …)` 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
- **`quality`** (`string`, _optional_): Quality tier. Higher is slower and costs more.
  - Default: `"540p"`
  - Options: `360p`, `540p`, `720p`, `1080p`
- **`duration`** (`number`, _optional_): Length of the output, in seconds.
  - Default: `5`
  - Range: 5–15 (step 1)
- **`generateAudio`** (`boolean`, _optional_): Whether the video gets a generated soundtrack. Audio can cost more.
  - Default: `true`
- **`aspectRatio`** (`string`, _optional_): Shape of the output as width:height. An auto or adaptive option follows the input image.
  - Default: `"16:9"`
  - Options: `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `2:3`, `3:2`, `21:9`
- **`imageUrls`** (`list<string>`, _required_): Input images, as URLs: frames to animate, or references for subject, style or composition.
  - Accepts: image URLs (max 7)

### 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",
    "imageUrls"
  ],
  "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."
    },
    "quality": {
      "type": "string",
      "enum": [
        "360p",
        "540p",
        "720p",
        "1080p"
      ],
      "default": "540p",
      "description": "Quality tier. Higher is slower and costs more."
    },
    "duration": {
      "type": "number",
      "minimum": 5,
      "maximum": 15,
      "multipleOf": 1,
      "default": 5,
      "description": "Length of the output, in seconds."
    },
    "generateAudio": {
      "type": "boolean",
      "default": true,
      "description": "Whether the video gets a generated soundtrack. Audio can cost more."
    },
    "aspectRatio": {
      "type": "string",
      "enum": [
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16",
        "2:3",
        "3:2",
        "21:9"
      ],
      "default": "16:9",
      "description": "Shape of the output as width:height. An auto or adaptive option follows the input image."
    },
    "imageUrls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri",
        "description": "image URL"
      },
      "maxItems": 7,
      "description": "Input images, as URLs: frames to animate, or references for subject, style or composition."
    }
  },
  "additionalProperties": false
}
```

### Required parameters example

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

```json
{
  "params": {
    "model": "pixverse-v6-fusion",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "duration": 5,
      "aspectRatio": "16:9",
      "imageUrls": [
        "https://cdn.example.com/input.jpg"
      ]
    }
  }
}
```

### 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": "pixverse-v6-fusion"
    }
  }
}
```

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

```json
{
  "items": [
    {
      "url": "https://cdn.picsart.com/…/result"
    }
  ],
  "model": "pixverse-v6-fusion"
}
```

### 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('pixverse-v6-fusion', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  duration: 5,
  aspectRatio: "16:9",
  imageUrls: [
    "https://cdn.example.com/input.jpg"
  ]
});

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("pixverse-v6-fusion", {
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
            "duration": 5,
            "aspectRatio": "16:9",
            "imageUrls": [
                "https://cdn.example.com/input.jpg",
            ],
        })

        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": "pixverse-v6-fusion",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "duration": 5,
      "aspectRatio": "16:9",
      "imageUrls": [
        "https://cdn.example.com/input.jpg"
      ]
    }
  }
}'
```

#### 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": "pixverse-v6-fusion",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "duration": 5,
      "aspectRatio": "16:9",
      "imageUrls": [
        "https://cdn.example.com/input.jpg"
      ]
    }
  }
}'
# → { "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 pixverse-v6-fusion  # this model's parameters
gen-ai pricing pixverse-v6-fusion  # quote before spending credits
gen-ai generate -m pixverse-v6-fusion \
  -p "A serene mountain lake at golden hour" \
  -i ./input.jpg \
  -d 5 \
  --ar 16:9
```

## Compatibility API (vendor parameters)

Alongside the unified API, the `pixverse/v2/reference-to-video` workflow takes PixVerse'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/pixverse/v2/reference-to-video/execute` (sync) · `POST …/submit` + `GET …/{taskId}/result` (async)
- **SDK**: `ai.apis.run('pixverse/v2/reference-to-video', params, { mode })` in TypeScript, `ai.apis.run("pixverse/v2/reference-to-video", params, mode=…)` in Python — params forwarded verbatim

### Vendor parameters

| Parameter | Type | Required | Default | Details |
| --- | --- | --- | --- | --- |
| `image_references` | `ReferenceImageItem[]` | yes | — | Reference images to fuse into the video. Each is uploaded to obtain an img_id. Max items depend on model: v4.5/v5 up to 3; v5.5+ up to 7. |
| └ `url` | `string` | yes | — | URL of the reference image. Uploaded to PixVerse to obtain an img_id. Formats: PNG, JPEG, JPG, WebP. Max 20MB / 10000px. |
| └ `type` | `string` | no | — | Reference role. Supported by v5.5 and above. · Options: `subject`, `background` |
| └ `ref_name` | `string` | no | — | Optional reference name (≤30 UTF-8 chars). Enables "@ref_name " mentions in the prompt. |
| `prompt` | `string` | yes | — | Text prompt describing the desired video. Max 5000 characters. Supports "@ref_name " mentions to reference uploaded images. |
| `model` | `string` | yes | — | PixVerse model version (reference-to-video requires v4.5+). · Options: `v4.5`, `v5`, `v5.5`, `v5.6`, `v6`, `c1` |
| `quality` | `string` | yes | — | Output resolution tier. Affects cost. · Options: `360p`, `540p`, `720p`, `1080p` |
| `aspect_ratio` | `string` | yes | — | Output aspect ratio. 2:3, 3:2 and 21:9 are supported only by v6 / c1. · Options: `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `2:3`, `3:2`, `21:9` |
| `duration` | `number` | yes | — | Video duration in seconds. Allowed values depend on model/quality: v4.5/v5: 5 or 8; v5.5/v5.6: 5, 8 or 10 (1080p excludes 10); c1: 1-15. Validated server-side. Affects cost. |
| `seed` | `number` | no | — | Random seed for reproducibility (0-2147483647). |
| `generate_audio_switch` | `boolean` | no | `false` | Generate synchronized audio. Supported by v5.6 / v6 / c1 only. |
| `options` | `object` | no | — | GenAI options for safety checks and Drive saving. |
| └ `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": {
    "image_references": [
      {
        "url": "your value here"
      }
    ],
    "prompt": "A serene mountain lake at golden hour, ultra detailed",
    "model": "v4.5",
    "quality": "360p",
    "aspect_ratio": "16:9",
    "duration": 0
  }
}
```

### 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 'pixverse/v2/reference-to-video' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('pixverse/v2/reference-to-video', {
  image_references: [
    {
      url: "your value here"
    }
  ],
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  model: "v4.5",
  quality: "360p",
  aspect_ratio: "16:9",
  duration: 0
}, {
  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 'pixverse/v2/reference-to-video' workflow directly — params are sent as-is.
        response = await ai.apis.run("pixverse/v2/reference-to-video", {
            "image_references": [
                {
                    "url": "your value here",
                },
            ],
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
            "model": "v4.5",
            "quality": "360p",
            "aspect_ratio": "16:9",
            "duration": 0,
        }, 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/pixverse/v2/reference-to-video/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "image_references": [
      {
        "url": "your value here"
      }
    ],
    "prompt": "A serene mountain lake at golden hour, ultra detailed",
    "model": "v4.5",
    "quality": "360p",
    "aspect_ratio": "16:9",
    "duration": 0
  }
}'
```

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

```bash
# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/pixverse/v2/reference-to-video/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "image_references": [
      {
        "url": "your value here"
      }
    ],
    "prompt": "A serene mountain lake at golden hour, ultra detailed",
    "model": "v4.5",
    "quality": "360p",
    "aspect_ratio": "16:9",
    "duration": 0
  }
}'
# → { "status": "success", "response": { "id": "wf_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/pixverse/v2/reference-to-video/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/pixverse-v6-fusion
- SDK and REST API (unified): https://picsart.com/api-platform/models/pixverse-v6-fusion#api
- Compatibility API (vendor parameters): https://picsart.com/api-platform/models/pixverse-v6-fusion#advanced
- Pricing: https://picsart.com/api-platform/models/pixverse-v6-fusion#pricing
- This document: https://picsart.com/api-platform/models/pixverse-v6-fusion/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