---
title: "WAN 2.6 720p - Create video from image"
method: POST
path: "/v1/ai/image-to-video/wan-v2-6-720p"
tags: ["image-to-video"]
---

# WAN 2.6 720p - Create video from image

`POST /v1/ai/image-to-video/wan-v2-6-720p`

## Request

- Base URL: `https://api.magnific.com`
- URL: `https://api.magnific.com/v1/ai/image-to-video/wan-v2-6-720p`
- Auth: API key in header `x-magnific-api-key`

Generate a 720p video from image using the WAN 2.6 model.

## Request body

- I2vWanV26720pRequestContent
  - `webhook_url` string, uri: Optional callback URL that will receive asynchronous notifications whenever the task changes status. The payload sent to this URL is the same as the corresponding GET endpoint response, but without the data field.
  - `prompt` string, required: Main description of the video - scene, characters, motion, camera moves, style. **Tips:** - Be specific about scenes and visual details - Describe camera movements (zoom, pan, tilt) - Mention lighting and atmosphere **Examples:** - Simple: "a cat sitting on a windowsill" - Detailed: "fluffy orange cat on wooden windowsill, looking at snow falling outside, soft warm lighting, camera slowly zooms in"
  - `duration` '5' | '10' | '15': Video duration in seconds: - `5`: Short clip, faster generation - `10`: Medium length, more developed action - `15`: Longer video, most detailed scenes
  - `negative_prompt` string: Things to avoid in the generated video. Use this to prevent unwanted elements. **Examples:** "blurry, low quality, watermark, text, distortion, extra limbs"
  - `enable_prompt_expansion` boolean: Enable AI prompt optimizer to expand shorter prompts into detailed scripts. Useful when you have a simple idea but want richer video output.
  - `shot_type` 'single' | 'multi': Shot composition type: - `single`: Continuous single shot (default, recommended for most use cases) - `multi`: Multi-shot sequence with scene transitions (requires enable_prompt_expansion=true)
  - `seed` integer: Random seed for reproducibility. Use the same seed with identical parameters to get similar results. Set to -1 for random seed.
  - `size` '1280*720' | '720*1280' | '960*960' | '1088*832' | '832*1088': Video size for the 720p resolution tier. Available aspect ratios: - `1280*720`: Landscape (16:9) - `720*1280`: Portrait (9:16) - `960*960`: Square (1:1) - `1088*832`: Standard landscape (4:3) - `832*1088`: Standard portrait (3:4)
  - `image` string, required: URL of the keyframe or base image to animate. Must be publicly accessible. **Supported formats:** JPEG, PNG, WebP **Dimension constraints:** Each dimension (width and height) must be between 240px and 8000px. **Maximum file size:** 10MB **Recommended:** High quality image with clear subject

## Response `200`

OK - Task created successfully

- CreateImageFromTextFlux200Response
  - `data` Task, required
    - `task_id` string, uuid, required: Task identifier
    - `status` 'CREATED' | 'IN_PROGRESS' | 'COMPLETED' | 'FAILED', required: Task status

## Other responses

- `400`: Bad Request - The server could not understand the request due to invalid syntax.
- `401`: Unauthorized - The client must authenticate itself to get the requested response.
- `500`: Internal Server Error - The server has encountered a situation it doesn't know how to handle.
- `503`: Service Unavailable

---

[API](https://skmtc.dev/magnific/apis/magnific-api.md) · [All operations](https://skmtc.dev/magnific/apis/magnific-api/llms.txt) · [OpenAPI document](https://skmtc.dev/magnific/apis/magnific-api/revisions/60711fb082c7?raw)