aliyun-video-style-repaint

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Video Style Repaint

视频风格重绘

Validation

验证

bash

mkdir -p output/aliyun-video-style-repaint
python -m py_compile skills/ai/video/aliyun-video-style-repaint/scripts/repaint_video.py && echo "py_compile_ok" > output/aliyun-video-style-repaint/validate.txt

Pass criteria: command exits 0 and

output/aliyun-video-style-repaint/validate.txt

is generated.

bash

mkdir -p output/aliyun-video-style-repaint
python -m py_compile skills/ai/video/aliyun-video-style-repaint/scripts/repaint_video.py && echo "py_compile_ok" > output/aliyun-video-style-repaint/validate.txt

通过条件：命令退出码为0，且成功生成

output/aliyun-video-style-repaint/validate.txt

文件。

Output And Evidence

输出与凭证

Save task IDs, polling responses, and final video URLs to
```
output/aliyun-video-style-repaint/
```
.
Keep at least one end-to-end run log for troubleshooting.

将任务ID、轮询响应和最终视频URL保存到
```
output/aliyun-video-style-repaint/
```
目录下。
至少保留一份端到端运行日志用于问题排查。

Prerequisites

前置要求

Install SDK (recommended in a venv):

bash

python3 -m venv .venv
. .venv/bin/activate
python -m pip install requests

Set

DASHSCOPE_API_KEY

in your environment, or add

dashscope_api_key

~/.alibabacloud/credentials

This API is only available in the Beijing region. You must use a Beijing-region API Key.

安装SDK（推荐在venv虚拟环境中安装）：

bash

python3 -m venv .venv
. .venv/bin/activate
python -m pip install requests

在环境变量中配置

DASHSCOPE_API_KEY

，或者将

dashscope_api_key

添加到

~/.alibabacloud/credentials

文件中。

该API仅支持北京区域，必须使用北京区域的API Key。

Critical model names

关键模型名称

```
video-style-transform
```
-- supports 8 preset artistic styles

```
video-style-transform
```
-- 支持8种预设艺术风格

Supported styles

支持的风格

Style ID	Name (EN)	Name (CN)
0	Japanese Manga	日式漫画
1	American Comics	美式漫画
2	Fresh Comics	清新漫画
3	3D Cartoon	3D 卡通
4	Chinese Cartoon	国风卡通
5	Paper Art	纸艺风格
6	Simple Illustration	简易插画
7	Chinese Ink Painting	国风水墨

风格ID	英文名称	中文名称
0	Japanese Manga	日式漫画
1	American Comics	美式漫画
2	Fresh Comics	清新漫画
3	3D Cartoon	3D 卡通
4	Chinese Cartoon	国风卡通
5	Paper Art	纸艺风格
6	Simple Illustration	简易插画
7	Chinese Ink Painting	国风水墨

API endpoint (async only)

API端点（仅支持异步调用）

POST https://dashscope.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis

Required headers:

Authorization: Bearer $DASHSCOPE_API_KEY

```
Content-Type: application/json
```
```
X-DashScope-Async: enable
```

POST https://dashscope.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis

必填请求头：

Authorization: Bearer $DASHSCOPE_API_KEY

```
Content-Type: application/json
```
```
X-DashScope-Async: enable
```

Normalized interface

标准化接口

Request

请求参数

```
video_url
```
(string, required) -- public HTTP/HTTPS URL of the input video
```
style
```
(integer, optional) -- style ID 0-7 (default: 0, Japanese Manga)
```
video_fps
```
(integer, optional) -- output frame rate, range [15, 25] (default: 15)
```
animate_emotion
```
(boolean, optional) -- facial expression optimization (default: true)
```
min_len
```
(integer, optional) -- output short-side pixels, 720 or 540 (default: 720)
```
use_SR
```
(boolean, optional) -- super-resolution enhancement (default: false)

```
video_url
```
（字符串，必填）-- 输入视频的公开HTTP/HTTPS链接
```
style
```
（整数，可选）-- 风格ID 0-7（默认值：0，日式漫画）
```
video_fps
```
（整数，可选）-- 输出帧率，取值范围 [15, 25]（默认值：15）
```
animate_emotion
```
（布尔值，可选）-- 面部表情优化（默认值：true）
```
min_len
```
（整数，可选）-- 输出短边像素，可选720或540（默认值：720）
```
use_SR
```
（布尔值，可选）-- 超分辨率增强（默认值：false）

Video input limits

视频输入限制

Formats: MP4, AVI, MKV, MOV, FLV, TS, MPG, MXF
Resolution: [256, 4096] pixels per side, aspect ratio max 1.8:1
Duration: up to 30 seconds
Max size: 100MB
URL: must be URL-encoded if contains non-ASCII characters

格式支持：MP4, AVI, MKV, MOV, FLV, TS, MPG, MXF
分辨率：每边像素范围[256, 4096]，宽高比最大为1.8:1
时长：最长30秒
最大大小：100MB
URL要求：如果包含非ASCII字符，必须进行URL编码

Response (task creation)

响应（任务创建）

```
output.task_id
```
(string) -- use for polling, valid 24 hours
```
output.task_status
```
(string) -- PENDING | RUNNING | SUSPENDED | SUCCEEDED | FAILED
```
request_id
```
(string)

```
output.task_id
```
（字符串）-- 用于轮询任务状态，有效期24小时
```
output.task_status
```
（字符串）-- 任务状态：PENDING | RUNNING | SUSPENDED | SUCCEEDED | FAILED
```
request_id
```
（字符串）

Response (task result)

响应（任务结果）

```
output.output_video_url
```
(string) -- result video URL
```
output.task_status
```
(string) -- final status
```
output.submit_time
```
(string) -- task submission time
```
output.scheduled_time
```
(string) -- task execution start time
```
output.end_time
```
(string) -- task completion time
```
usage.duration
```
(integer) -- video duration in seconds
```
usage.SR
```
(integer) -- resolution used

```
output.output_video_url
```
（字符串）-- 结果视频URL
```
output.task_status
```
（字符串）-- 任务最终状态
```
output.submit_time
```
（字符串）-- 任务提交时间
```
output.scheduled_time
```
（字符串）-- 任务执行开始时间
```
output.end_time
```
（字符串）-- 任务完成时间
```
usage.duration
```
（整数）-- 视频时长，单位为秒
```
usage.SR
```
（整数）-- 所用分辨率

Quick start (Python + HTTP)

快速上手（Python + HTTP）

python

import os
import json
import time
import requests

API_KEY = os.getenv("DASHSCOPE_API_KEY")
BASE_URL = "https://dashscope.aliyuncs.com/api/v1"

def create_style_repaint_task(video_url: str, style: int = 0) -> str:
    """Create a video style repaint task and return task_id."""
    payload = {
        "model": "video-style-transform",
        "input": {
            "video_url": video_url,
        },
        "parameters": {
            "style": style,
            "video_fps": 15,
        },
    }
    resp = requests.post(
        f"{BASE_URL}/services/aigc/video-generation/video-synthesis",
        headers={
            "Authorization": f"Bearer {API_KEY}",
            "Content-Type": "application/json",
            "X-DashScope-Async": "enable",
        },
        json=payload,
    )
    resp.raise_for_status()
    data = resp.json()
    return data["output"]["task_id"]


def poll_task(task_id: str, interval: int = 15) -> dict:
    """Poll until task completes. Returns final response."""
    while True:
        resp = requests.get(
            f"{BASE_URL}/tasks/{task_id}",
            headers={"Authorization": f"Bearer {API_KEY}"},
        )
        resp.raise_for_status()
        data = resp.json()
        status = data["output"]["task_status"]
        if status in ("SUCCEEDED", "FAILED", "CANCELED", "SUSPENDED"):
            return data
        time.sleep(interval)

python

import os
import json
import time
import requests

API_KEY = os.getenv("DASHSCOPE_API_KEY")
BASE_URL = "https://dashscope.aliyuncs.com/api/v1"

def create_style_repaint_task(video_url: str, style: int = 0) -> str:
    """创建视频风格重绘任务并返回task_id。"""
    payload = {
        "model": "video-style-transform",
        "input": {
            "video_url": video_url,
        },
        "parameters": {
            "style": style,
            "video_fps": 15,
        },
    }
    resp = requests.post(
        f"{BASE_URL}/services/aigc/video-generation/video-synthesis",
        headers={
            "Authorization": f"Bearer {API_KEY}",
            "Content-Type": "application/json",
            "X-DashScope-Async: enable",
        },
        json=payload,
    )
    resp.raise_for_status()
    data = resp.json()
    return data["output"]["task_id"]


def poll_task(task_id: str, interval: int = 15) -> dict:
    """轮询直到任务完成，返回最终响应结果。"""
    while True:
        resp = requests.get(
            f"{BASE_URL}/tasks/{task_id}",
            headers={"Authorization": f"Bearer {API_KEY}"},
        )
        resp.raise_for_status()
        data = resp.json()
        status = data["output"]["task_status"]
        if status in ("SUCCEEDED", "FAILED", "CANCELED", "SUSPENDED"):
            return data
        time.sleep(interval)

Error handling

错误处理

Error	Likely cause	Action
401/403	Missing or invalid `DASHSCOPE_API_KEY`	Check env var or credentials file
400 `InvalidParameter`	Unsupported video format, bad dimensions, invalid style	Validate parameters
"does not support synchronous calls"	Missing `X-DashScope-Async: enable` header	Add required header
429	Rate limit or quota	Retry with backoff

错误	可能原因	解决措施
401/403	缺少 `DASHSCOPE_API_KEY` 或密钥无效	检查环境变量或凭证文件
400 `InvalidParameter`	不支持的视频格式、尺寸不合法、风格参数无效	校验输入参数
"does not support synchronous calls"	缺少 `X-DashScope-Async: enable` 请求头	添加必填请求头
429	触发限流或配额不足	退避后重试

Output location

输出位置

Default output:

output/aliyun-video-style-repaint/videos/

Override base dir with
```
OUTPUT_DIR
```
.

默认输出路径：

output/aliyun-video-style-repaint/videos/

可通过
```
OUTPUT_DIR
```
环境变量覆盖基础目录。

Anti-patterns

错误用法

Do not use model names other than
```
video-style-transform
```
.
Do not call this API synchronously -- async header is required.
Do not use style IDs outside 0-7 range.
Video URLs expire after 24 hours; download and persist immediately.
Do not use Singapore endpoint -- this API is Beijing-region only.

不要使用
```
video-style-transform
```
以外的模型名。
不要同步调用该API -- 必须携带异步请求头。
不要使用0-7范围以外的风格ID。
视频URL有效期为24小时，请立即下载持久化。
不要使用新加坡区域端点 -- 该API仅支持北京区域。

Workflow

工作流程

Confirm user intent: select desired artistic style from the 8 presets.
Prepare video URL with valid format and dimensions.
Configure parameters (style, fps, resolution, super-resolution).
Create async task and poll for results.
Download and save transformed video before URL expiration.

确认用户需求：从8种预设风格中选择目标艺术风格。
准备符合格式和尺寸要求的视频URL。
配置参数（风格、帧率、分辨率、超分辨率）。
创建异步任务并轮询获取结果。
在URL过期前下载并保存转换后的视频。

References

参考资料

See
```
references/api_reference.md
```
for full HTTP API details.
See
```
references/sources.md
```
for source links.

完整HTTP API详情请查看
```
references/api_reference.md
```
。
源链接请查看
```
references/sources.md
```
。