wan-video

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Wan Video Generation

Wan视频生成

Generate AI videos through AceDataCloud's Wan (Alibaba) API.

Setup: See authentication for token setup.

通过AceDataCloud的阿里Wan API生成AI视频。

设置： 请查看身份验证了解令牌设置。

Quick Start

快速开始

bash

curl -X POST https://api.acedata.cloud/wan/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"action": "text2video", "prompt": "a dolphin jumping through ocean waves at golden hour", "model": "wan2.6-t2v"}'

Async: See async task polling. Poll via
POST /wan/tasks
with
{"id": "..."}
.

bash

curl -X POST https://api.acedata.cloud/wan/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"action": "text2video", "prompt": "a dolphin jumping through ocean waves at golden hour", "model": "wan2.6-t2v"}'

异步处理： 请查看异步任务轮询。通过
POST /wan/tasks
接口并传入
{"id": "..."}
进行轮询。

Models

模型

Model	Type	Best For
`wan2.6-t2v`	Text-to-Video	Creating video from text description
`wan2.6-i2v`	Image-to-Video	Animating a still image into video
`wan2.6-r2v`	Reference Video-to-Video	Character extraction and transfer from reference video
`wan2.6-i2v-flash`	Image-to-Video (Fast)	Quick image-to-video generation

模型	类型	适用场景
`wan2.6-t2v`	文本转视频	根据文本描述创建视频
`wan2.6-i2v`	图片转视频	将静态图片动效化为视频
`wan2.6-r2v`	参考视频转视频	从参考视频中提取角色并迁移
`wan2.6-i2v-flash`	图片转视频（快速版）	快速生成图片转视频内容

Workflows

工作流

1. Text-to-Video

1. 文本转视频

json

POST /wan/videos
{
  "action": "text2video",
  "prompt": "a time-lapse of flowers blooming in a meadow",
  "model": "wan2.6-t2v",
  "resolution": "720P",
  "duration": 5
}

json

POST /wan/videos
{
  "action": "text2video",
  "prompt": "a time-lapse of flowers blooming in a meadow",
  "model": "wan2.6-t2v",
  "resolution": "720P",
  "duration": 5
}

2. Image-to-Video

2. 图片转视频

Animate a still image into a video clip.

json

POST /wan/videos
{
  "action": "image2video",
  "prompt": "gentle wind blows through the scene",
  "model": "wan2.6-i2v",
  "image_url": "https://example.com/landscape.jpg",
  "resolution": "720P",
  "duration": 5
}

将静态图片动效化为视频片段。

json

POST /wan/videos
{
  "action": "image2video",
  "prompt": "gentle wind blows through the scene",
  "model": "wan2.6-i2v",
  "image_url": "https://example.com/landscape.jpg",
  "resolution": "720P",
  "duration": 5
}

3. Image-to-Video (Flash)

3. 图片转视频（快速版）

Faster image-to-video generation with reduced latency.

json

POST /wan/videos
{
  "action": "image2video",
  "prompt": "camera slowly pans across the landscape",
  "model": "wan2.6-i2v-flash",
  "image_url": "https://example.com/scene.jpg"
}

以更低延迟快速生成图片转视频内容。

json

POST /wan/videos
{
  "action": "image2video",
  "prompt": "camera slowly pans across the landscape",
  "model": "wan2.6-i2v-flash",
  "image_url": "https://example.com/scene.jpg"
}

4. Reference Video Transfer

4. 参考视频迁移

Extract characters or timbres from a reference video and transfer them into a new generation.

json

POST /wan/videos
{
  "action": "text2video",
  "prompt": "the character walks through a futuristic city at night",
  "model": "wan2.6-r2v",
  "reference_video_urls": ["https://example.com/reference.mp4"]
}

从参考视频中提取角色或音色，并迁移到新生成的视频中。

json

POST /wan/videos
{
  "action": "text2video",
  "prompt": "the character walks through a futuristic city at night",
  "model": "wan2.6-r2v",
  "reference_video_urls": ["https://example.com/reference.mp4"]
}

5. Multi-Cut Editing

5. 多镜头剪辑

Generate a video with multiple shots rather than a single continuous take.

json

POST /wan/videos
{
  "action": "text2video",
  "prompt": "a chef preparing a meal in a busy kitchen",
  "model": "wan2.6-t2v",
  "shot_type": "multi",
  "duration": 10
}

生成包含多个镜头而非单一连续镜头的视频。

json

POST /wan/videos
{
  "action": "text2video",
  "prompt": "a chef preparing a meal in a busy kitchen",
  "model": "wan2.6-t2v",
  "shot_type": "multi",
  "duration": 10
}

6. Video with Audio

6. 带音频的视频

Enable audio generation alongside the video.

json

POST /wan/videos
{
  "action": "text2video",
  "prompt": "ocean waves crashing on a rocky shore",
  "model": "wan2.6-t2v",
  "audio": true
}

生成视频的同时启用音频生成功能。

json

POST /wan/videos
{
  "action": "text2video",
  "prompt": "ocean waves crashing on a rocky shore",
  "model": "wan2.6-t2v",
  "audio": true
}

Parameters

参数说明

Parameter	Required	Values	Description
`action`	Yes	`"text2video"` , `"image2video"`	Action type
`prompt`	Yes	string	Scene description
`model`	Yes	`"wan2.6-t2v"` , `"wan2.6-i2v"` , `"wan2.6-r2v"` , `"wan2.6-i2v-flash"`	Model
`image_url`	For image2video	string	Source image URL (required for image-to-video)
`negative_prompt`	No	string (max 500 chars)	Content to exclude from generation
`reference_video_urls`	For r2v	array of strings	Reference videos for character/timbre extraction
`shot_type`	No	`"single"` , `"multi"`	Continuous shot or multi-cut editing
`audio`	No	boolean	Enable audio in the generated video
`audio_url`	No	string	Reference audio URL
`resolution`	No	`"480P"` , `"720P"` , `"1080P"`	Output resolution (default: 720P)
`size`	No	string	The size of the generated video
`duration`	No	`5` , `10` , `15`	Video duration in seconds
`prompt_extend`	No	boolean	Enable LLM-based prompt rewriting
`callback_url`	No	string	Async webhook notification URL

参数	是否必填	可选值	描述
`action`	是	`"text2video"` , `"image2video"`	操作类型
`prompt`	是	字符串	场景描述
`model`	是	`"wan2.6-t2v"` , `"wan2.6-i2v"` , `"wan2.6-r2v"` , `"wan2.6-i2v-flash"`	模型
`image_url`	图片转视频场景必填	字符串	源图片URL（图片转视频场景必填）
`negative_prompt`	否	字符串（最多500字符）	生成时需要排除的内容
`reference_video_urls`	r2v模型必填	字符串数组	用于提取角色/音色的参考视频
`shot_type`	否	`"single"` , `"multi"`	单一连续镜头或多镜头剪辑
`audio`	否	布尔值	启用生成视频中的音频
`audio_url`	否	字符串	参考音频URL
`resolution`	否	`"480P"` , `"720P"` , `"1080P"`	输出分辨率（默认：720P）
`size`	否	字符串	生成视频的尺寸
`duration`	否	`5` , `10` , `15`	视频时长（秒）
`prompt_extend`	否	布尔值	启用基于LLM的提示词重写
`callback_url`	否	字符串	异步回调通知URL

Gotchas

注意事项

```
image_url
```
is required for
```
wan2.6-i2v
```
and
```
wan2.6-i2v-flash
```
models
```
reference_video_urls
```
is used only with
```
wan2.6-r2v
```
for character/timbre transfer
```
negative_prompt
```
has a maximum length of 500 characters
Supported durations are 5, 10, or 15 seconds only
Default resolution is 720P; use 1080P for higher quality at increased cost
```
shot_type: "multi"
```
produces multi-cut edits rather than a single continuous shot

MCP:
pip install mcp-wan
| Hosted:
https://wan.mcp.acedata.cloud/mcp
| See all MCP servers

使用
```
wan2.6-i2v
```
和
```
wan2.6-i2v-flash
```
模型时，
```
image_url
```
为必填项
```
reference_video_urls
```
仅在使用
```
wan2.6-r2v
```
模型进行角色/音色迁移时生效
```
negative_prompt
```
的最大长度为500字符
仅支持5、10或15秒的视频时长
默认分辨率为720P；使用1080P可获得更高画质，但成本会增加
```
shot_type: "multi"
```
将生成多镜头剪辑视频，而非单一连续镜头

MCP：
pip install mcp-wan
| 托管地址：
https://wan.mcp.acedata.cloud/mcp
| 查看所有MCP服务器