aliyun-wan-digital-human

Name: aliyun-wan-digital-human
Author: cinience

397stars34forks

How to install aliyun-wan-digital-human?

cinience/alicloud-skills/aliyun-wan-digital-human

$npx -y skills add cinience/alicloud-skills --skill aliyun-wan-digital-human

Installs into the current project.

Summary

Use when generating talking, singing, or presentation videos from a single character image and audio with Alibaba Cloud Model Studio digital-human model wan2.2-s2v. Use when creating narrated avatar videos, singing portraits, or broadcast-style talking-head clips.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Digital Human
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-wan-digital-human
9	python -m py_compile skills/ai/video/aliyun-wan-digital-human/scripts/prepare_digital_human_request.py && echo "py_compile_ok" > output/aliyun-wan-digital-human/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-wan-digital-human/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, chosen resolution, and task polling snapshots under `output/aliyun-wan-digital-human/`.
17	- Record image/audio URLs and whether the input image passed detection.
18
19	Use this skill for image + audio driven speaking, singing, or presenting characters.
20
21	## Critical model names
22
23	Use these exact model strings:
24	- `wan2.2-s2v-detect`
25	- `wan2.2-s2v`
26
27	Selection guidance:
28	- Run `wan2.2-s2v-detect` first to validate the image.
29	- Use `wan2.2-s2v` for the actual video generation job.
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 audio should contain clear speech or singing, and input image should depict a clear subject.
36
37	## Normalized interface (video.digital_human)
38
39	### Detect Request
40	- `model` (string, optional): default `wan2.2-s2v-detect`
41	- `image_url` (string, required)
42
43	### Generate Request
44	- `model` (string, optional): default `wan2.2-s2v`
45	- `image_url` (string, required)
46	- `audio_url` (string, required)
47	- `resolution` (string, optional): `480P` or `720P`
48	- `scenario` (string, optional): `talk`, `sing`, or `perform`
49
50	### Response
51	- `task_id` (string)
52	- `task_status` (string)
53	- `video_url` (string, when finished)
54
55	## Quick start
56
57	```bash
58	python skills/ai/video/aliyun-wan-digital-human/scripts/prepare_digital_human_request.py \
59	--image-url "https://example.com/anchor.png" \
60	--audio-url "https://example.com/voice.mp3" \
61	--resolution 720P \
62	--scenario talk
63	```
64
65	## Operational guidance
66
67	- Use a portrait, half-body, or full-body image with a clear face and stable framing.
68	- Match audio length to the desired output duration; the output follows the audio length up to the model limit.
69	- Keep image and audio as public HTTP/HTTPS URLs.
70	- If the image fails detection, do not proceed directly to video generation.
71
72	## Output location
73
74	- Default output: `output/aliyun-wan-digital-human/request.json`
75	- Override base dir with `OUTPUT_DIR`.
76
77	## References
78
79	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-wan-digital-human

397stars34forks

View on GitHub

How to install aliyun-wan-digital-human?

cinience/alicloud-skills/aliyun-wan-digital-human

$npx -y skills add cinience/alicloud-skills --skill aliyun-wan-digital-human

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Digital Human
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-wan-digital-human
9	python -m py_compile skills/ai/video/aliyun-wan-digital-human/scripts/prepare_digital_human_request.py && echo "py_compile_ok" > output/aliyun-wan-digital-human/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-wan-digital-human/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, chosen resolution, and task polling snapshots under `output/aliyun-wan-digital-human/`.
17	- Record image/audio URLs and whether the input image passed detection.
18
19	Use this skill for image + audio driven speaking, singing, or presenting characters.
20
21	## Critical model names
22
23	Use these exact model strings:
24	- `wan2.2-s2v-detect`
25	- `wan2.2-s2v`
26
27	Selection guidance:
28	- Run `wan2.2-s2v-detect` first to validate the image.
29	- Use `wan2.2-s2v` for the actual video generation job.
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 audio should contain clear speech or singing, and input image should depict a clear subject.
36
37	## Normalized interface (video.digital_human)
38
39	### Detect Request
40	- `model` (string, optional): default `wan2.2-s2v-detect`
41	- `image_url` (string, required)
42
43	### Generate Request
44	- `model` (string, optional): default `wan2.2-s2v`
45	- `image_url` (string, required)
46	- `audio_url` (string, required)
47	- `resolution` (string, optional): `480P` or `720P`
48	- `scenario` (string, optional): `talk`, `sing`, or `perform`
49
50	### Response
51	- `task_id` (string)
52	- `task_status` (string)
53	- `video_url` (string, when finished)
54
55	## Quick start
56
57	```bash
58	python skills/ai/video/aliyun-wan-digital-human/scripts/prepare_digital_human_request.py \
59	--image-url "https://example.com/anchor.png" \
60	--audio-url "https://example.com/voice.mp3" \
61	--resolution 720P \
62	--scenario talk
63	```
64
65	## Operational guidance
66
67	- Use a portrait, half-body, or full-body image with a clear face and stable framing.
68	- Match audio length to the desired output duration; the output follows the audio length up to the model limit.
69	- Keep image and audio as public HTTP/HTTPS URLs.
70	- If the image fails detection, do not proceed directly to video generation.
71
72	## Output location
73
74	- Default output: `output/aliyun-wan-digital-human/request.json`
75	- Override base dir with `OUTPUT_DIR`.
76
77	## References
78
79	- `references/sources.md`

People who liked this also viewed

6 picks

Type