alicloud-ai-video-wan-r2v

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Category: provider

分类：供应商

Model Studio Wan R2V

Use Wan R2V for reference-to-video generation. This is different from i2v (single image to video).

使用Wan R2V进行参考转视频生成。这与i2v（单图转视频）不同。

Critical model name

关键模型名称

Use ONLY this exact model string:

```
wan2.6-r2v-flash
```

请仅使用以下精确的模型字符串：

```
wan2.6-r2v-flash
```

Prerequisites

前置条件

Install SDK in a virtual environment:

bash

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

Set

DASHSCOPE_API_KEY

in your environment, or add

dashscope_api_key

~/.alibabacloud/credentials

在虚拟环境中安装SDK：

bash

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

在环境变量中设置

DASHSCOPE_API_KEY

，或者在

~/.alibabacloud/credentials

中添加

dashscope_api_key

。

Normalized interface (video.generate_reference)

标准化接口（video.generate_reference）

Request

请求参数

```
prompt
```
(string, required)
```
reference_video
```
(string | bytes, required)
```
reference_image
```
(string | bytes, optional)
```
duration
```
(number, optional)
```
fps
```
(number, optional)
```
size
```
(string, optional)
```
seed
```
(int, optional)

```
prompt
```
（字符串，必填）
```
reference_video
```
（字符串 | 字节，必填）
```
reference_image
```
（字符串 | 字节，可选）
```
duration
```
（数字，可选）
```
fps
```
（数字，可选）
```
size
```
（字符串，可选）
```
seed
```
（整数，可选）

Response

响应参数

```
video_url
```
(string)
```
task_id
```
(string, when async)
```
request_id
```
(string)

```
video_url
```
（字符串）
```
task_id
```
（字符串，异步请求时返回）
```
request_id
```
（字符串）

Async handling

异步处理

Prefer async submission for production traffic.
Poll task result with 15-20s intervals.
Stop polling when
```
SUCCEEDED
```
or terminal failure status is returned.

生产环境流量优先使用异步提交。
以15-20秒的间隔轮询任务结果。
当返回
```
SUCCEEDED
```
或终端失败状态时停止轮询。

Local helper script

本地辅助脚本

Prepare a normalized request JSON and validate response schema:

bash

.venv/bin/python skills/ai/video/alicloud-ai-video-wan-r2v/scripts/prepare_r2v_request.py \
  --prompt "Generate a short montage with consistent character style" \
  --reference-video "https://example.com/reference.mp4"

准备标准化的请求JSON并验证响应 schema：

bash

.venv/bin/python skills/ai/video/alicloud-ai-video-wan-r2v/scripts/prepare_r2v_request.py \
  --prompt "Generate a short montage with consistent character style" \
  --reference-video "https://example.com/reference.mp4"

Output location

输出位置

Default output:
```
output/ai-video-wan-r2v/videos/
```
Override base dir with
```
OUTPUT_DIR
```
.

默认输出路径：
```
output/ai-video-wan-r2v/videos/
```
可通过
```
OUTPUT_DIR
```
覆盖基础目录。

References

参考资料

```
references/sources.md
```

```
references/sources.md
```