aliyun-liveportrait

Name: aliyun-liveportrait
Author: cinience

397stars34forks

How to install aliyun-liveportrait?

cinience/alicloud-skills/aliyun-liveportrait

$npx -y skills add cinience/alicloud-skills --skill aliyun-liveportrait

Installs into the current project.

Summary

Use when generating lightweight talking-head portrait videos with Alibaba Cloud Model Studio LivePortrait (liveportrait) from a detected portrait image and speech audio. Use when you need long-form or simple broadcast-style portrait animation beyond the typical short expressive

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio LivePortrait
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-liveportrait
9	python -m py_compile skills/ai/video/aliyun-liveportrait/scripts/prepare_liveportrait_request.py && echo "py_compile_ok" > output/aliyun-liveportrait/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-liveportrait/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, template choice, and task polling snapshots under `output/aliyun-liveportrait/`.
17	- Record the exact portrait/audio URLs and motion-strength related parameters.
18
19	Use LivePortrait when the job is lightweight portrait animation with speech audio, especially for longer clips or simpler presenter-style motion.
20
21	## Critical model names
22
23	Use these exact model strings:
24	- `liveportrait-detect`
25	- `liveportrait`
26
27	Selection guidance:
28	- Run `liveportrait-detect` first to verify the portrait image.
29	- Use `liveportrait` for the actual video generation task.
30
31	## Prerequisites
32
33	- China mainland (Beijing) only.
34	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
35	- Input image and audio must be public HTTP/HTTPS URLs.
36
37	## Normalized interface (video.liveportrait)
38
39	### Detect Request
40	- `model` (string, optional): default `liveportrait-detect`
41	- `image_url` (string, required)
42
43	### Generate Request
44	- `model` (string, optional): default `liveportrait`
45	- `image_url` (string, required)
46	- `audio_url` (string, required)
47	- `template_id` (string, optional): `normal`, `calm`, or `active`
48	- `eye_move_freq` (number, optional): `0` to `1`
49	- `video_fps` (int, optional): `15` to `30`
50	- `mouth_move_strength` (number, optional): `0` to `1.5`
51	- `paste_back` (bool, optional)
52	- `head_move_strength` (number, optional): `0` to `1`
53
54	### Response
55	- `task_id` (string)
56	- `task_status` (string)
57	- `video_url` (string, when finished)
58
59	## Quick start
60
61	```bash
62	python skills/ai/video/aliyun-liveportrait/scripts/prepare_liveportrait_request.py \
63	--image-url "https://example.com/portrait.png" \
64	--audio-url "https://example.com/speech.mp3" \
65	--template-id calm \
66	--video-fps 24 \
67	--paste-back
68	```
69
70	## Operational guidance
71
72	- Use a clear, front-facing portrait with low occlusion.
73	- Keep the audio clean and voice-dominant.
74	- `paste_back=false` outputs only the generated face region; keep it `true` for standard talking-head output.
75	- LivePortrait is a better fit than EMO when you need longer, simpler presenter-style clips.
76
77	## Output location
78
79	- Default output: `output/aliyun-liveportrait/request.json`
80	- Override base dir with `OUTPUT_DIR`.
81
82	## References
83
84	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-liveportrait

397stars34forks

View on GitHub

How to install aliyun-liveportrait?

cinience/alicloud-skills/aliyun-liveportrait

$npx -y skills add cinience/alicloud-skills --skill aliyun-liveportrait

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio LivePortrait
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-liveportrait
9	python -m py_compile skills/ai/video/aliyun-liveportrait/scripts/prepare_liveportrait_request.py && echo "py_compile_ok" > output/aliyun-liveportrait/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-liveportrait/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, template choice, and task polling snapshots under `output/aliyun-liveportrait/`.
17	- Record the exact portrait/audio URLs and motion-strength related parameters.
18
19	Use LivePortrait when the job is lightweight portrait animation with speech audio, especially for longer clips or simpler presenter-style motion.
20
21	## Critical model names
22
23	Use these exact model strings:
24	- `liveportrait-detect`
25	- `liveportrait`
26
27	Selection guidance:
28	- Run `liveportrait-detect` first to verify the portrait image.
29	- Use `liveportrait` for the actual video generation task.
30
31	## Prerequisites
32
33	- China mainland (Beijing) only.
34	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
35	- Input image and audio must be public HTTP/HTTPS URLs.
36
37	## Normalized interface (video.liveportrait)
38
39	### Detect Request
40	- `model` (string, optional): default `liveportrait-detect`
41	- `image_url` (string, required)
42
43	### Generate Request
44	- `model` (string, optional): default `liveportrait`
45	- `image_url` (string, required)
46	- `audio_url` (string, required)
47	- `template_id` (string, optional): `normal`, `calm`, or `active`
48	- `eye_move_freq` (number, optional): `0` to `1`
49	- `video_fps` (int, optional): `15` to `30`
50	- `mouth_move_strength` (number, optional): `0` to `1.5`
51	- `paste_back` (bool, optional)
52	- `head_move_strength` (number, optional): `0` to `1`
53
54	### Response
55	- `task_id` (string)
56	- `task_status` (string)
57	- `video_url` (string, when finished)
58
59	## Quick start
60
61	```bash
62	python skills/ai/video/aliyun-liveportrait/scripts/prepare_liveportrait_request.py \
63	--image-url "https://example.com/portrait.png" \
64	--audio-url "https://example.com/speech.mp3" \
65	--template-id calm \
66	--video-fps 24 \
67	--paste-back
68	```
69
70	## Operational guidance
71
72	- Use a clear, front-facing portrait with low occlusion.
73	- Keep the audio clean and voice-dominant.
74	- `paste_back=false` outputs only the generated face region; keep it `true` for standard talking-head output.
75	- LivePortrait is a better fit than EMO when you need longer, simpler presenter-style clips.
76
77	## Output location
78
79	- Default output: `output/aliyun-liveportrait/request.json`
80	- Override base dir with `OUTPUT_DIR`.
81
82	## References
83
84	- `references/sources.md`

People who liked this also viewed

6 picks

Type