aliyun-liveportrait

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Category: provider

分类：provider

Model Studio LivePortrait

Validation

验证

bash

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

Pass criteria: command exits 0 and

output/aliyun-liveportrait/validate.txt

is generated.

bash

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

通过标准：命令退出码为0，且成功生成

output/aliyun-liveportrait/validate.txt

文件。

Output And Evidence

输出与证明材料

Save normalized request payloads, template choice, and task polling snapshots under
```
output/aliyun-liveportrait/
```
.
Record the exact portrait/audio URLs and motion-strength related parameters.

Use LivePortrait when the job is lightweight portrait animation with speech audio, especially for longer clips or simpler presenter-style motion.

请将标准化请求负载、模板选择结果和任务轮询快照保存至
```
output/aliyun-liveportrait/
```
目录下。
记录准确的肖像/音频URL以及动效强度相关参数。

当任务为带语音音频的轻量级肖像动画，尤其是生成长片段或更简单的主持人风格动效时，适合使用LivePortrait。

Critical model names

关键模型名称

Use these exact model strings:

```
liveportrait-detect
```
```
liveportrait
```

Selection guidance:

Run
```
liveportrait-detect
```
first to verify the portrait image.
Use
```
liveportrait
```
for the actual video generation task.

请使用以下准确的模型字符串：

```
liveportrait-detect
```
```
liveportrait
```

选择指南：

首先运行
```
liveportrait-detect
```
来校验肖像图片。
使用
```
liveportrait
```
执行实际的视频生成任务。

Prerequisites

前置条件

China mainland (Beijing) only.

Set

DASHSCOPE_API_KEY

in your environment, or add

dashscope_api_key

~/.alibabacloud/credentials

Input image and audio must be public HTTP/HTTPS URLs.

仅支持中国大陆（北京）区域使用。

请在环境变量中设置

DASHSCOPE_API_KEY

，或将

dashscope_api_key

添加至

~/.alibabacloud/credentials

文件中。

输入的图片和音频必须是公开可访问的HTTP/HTTPS URL。

Normalized interface (video.liveportrait)

标准化接口（video.liveportrait）

Detect Request

检测请求

```
model
```
(string, optional): default
```
liveportrait-detect
```
```
image_url
```
(string, required)

```
model
```
（字符串，可选）：默认值为
```
liveportrait-detect
```
```
image_url
```
（字符串，必填）

Generate Request

生成请求

```
model
```
(string, optional): default
```
liveportrait
```
```
image_url
```
(string, required)
```
audio_url
```
(string, required)
```
template_id
```
(string, optional):
```
normal
```
,
```
calm
```
, or
```
active
```
```
eye_move_freq
```
(number, optional):
```
0
```
to
```
1
```
```
video_fps
```
(int, optional):
```
15
```
to
```
30
```
```
mouth_move_strength
```
(number, optional):
```
0
```
to
```
1.5
```
```
paste_back
```
(bool, optional)
```
head_move_strength
```
(number, optional):
```
0
```
to
```
1
```

```
model
```
（字符串，可选）：默认值为
```
liveportrait
```
```
image_url
```
（字符串，必填）
```
audio_url
```
（字符串，必填）
```
template_id
```
（字符串，可选）：可选值为
```
normal
```
、
```
calm
```
或
```
active
```
```
eye_move_freq
```
（数值，可选）：取值范围
```
0
```
到
```
1
```
```
video_fps
```
（整数，可选）：取值范围
```
15
```
到
```
30
```
```
mouth_move_strength
```
（数值，可选）：取值范围
```
0
```
到
```
1.5
```
```
paste_back
```
（布尔值，可选）
```
head_move_strength
```
（数值，可选）：取值范围
```
0
```
到
```
1
```

Response

返回结果

```
task_id
```
(string)
```
task_status
```
(string)
```
video_url
```
(string, when finished)

```
task_id
```
（字符串）
```
task_status
```
（字符串）
```
video_url
```
（字符串，任务完成时返回）

Quick start

快速开始

bash

python skills/ai/video/aliyun-liveportrait/scripts/prepare_liveportrait_request.py \
  --image-url "https://example.com/portrait.png" \
  --audio-url "https://example.com/speech.mp3" \
  --template-id calm \
  --video-fps 24 \
  --paste-back

bash

python skills/ai/video/aliyun-liveportrait/scripts/prepare_liveportrait_request.py \
  --image-url "https://example.com/portrait.png" \
  --audio-url "https://example.com/speech.mp3" \
  --template-id calm \
  --video-fps 24 \
  --paste-back

Operational guidance

使用指南

Use a clear, front-facing portrait with low occlusion.
Keep the audio clean and voice-dominant.
```
paste_back=false
```
outputs only the generated face region; keep it
```
true
```
for standard talking-head output.
LivePortrait is a better fit than EMO when you need longer, simpler presenter-style clips.

请使用清晰、低遮挡的正面肖像图片。
请使用干净、以人声为主的音频。
```
paste_back=false
```
时仅输出生成的人脸区域；如需标准的说话人肖像输出，请将其设置为
```
true
```
。
当你需要生成长时长、更简单的主持人风格片段时，相比EMO，LivePortrait是更合适的选择。

Output location

输出路径

Default output:
```
output/aliyun-liveportrait/request.json
```
Override base dir with
```
OUTPUT_DIR
```
.

默认输出路径：
```
output/aliyun-liveportrait/request.json
```
可通过
```
OUTPUT_DIR
```
环境变量覆盖基础目录。

References

参考文档

```
references/sources.md
```

```
references/sources.md
```