aliyun-animate-anyone

Name: aliyun-animate-anyone
Author: cinience

397stars34forks

How to install aliyun-animate-anyone?

cinience/alicloud-skills/aliyun-animate-anyone

$npx -y skills add cinience/alicloud-skills --skill aliyun-animate-anyone

Installs into the current project.

Summary

Use when generating dance or motion-transfer videos with Alibaba Cloud Model Studio AnimateAnyone (animate-anyone-gen2) using a detected character image and an action template. Use when cloning motion from a dance/action video into a target character image.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio AnimateAnyone
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-animate-anyone
9	python -m py_compile skills/ai/video/aliyun-animate-anyone/scripts/prepare_animate_anyone_request.py && echo "py_compile_ok" > output/aliyun-animate-anyone/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-animate-anyone/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, detection outputs, template IDs, and task polling snapshots under `output/aliyun-animate-anyone/`.
17	- Record whether the result should keep the reference image background or the source video background.
18
19	Use AnimateAnyone when the task needs motion transfer from a template video rather than plain talking-head animation.
20
21	## Critical model names
22
23	Use these exact model strings:
24	- `animate-anyone-detect-gen2`
25	- `animate-anyone-template-gen2`
26	- `animate-anyone-gen2`
27
28	Selection guidance:
29	- Run image detection first.
30	- Run template generation on the source motion video.
31	- Use `animate-anyone-gen2` for the final video job.
32
33	## Prerequisites
34
35	- China mainland (Beijing) only.
36	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
37	- Input files must be public HTTP/HTTPS URLs.
38
39	## Normalized interface (video.animate_anyone)
40
41	### Detect Request
42	- `model` (string, optional): default `animate-anyone-detect-gen2`
43	- `image_url` (string, required)
44
45	### Template Request
46	- `model` (string, optional): default `animate-anyone-template-gen2`
47	- `video_url` (string, required)
48
49	### Generate Request
50	- `model` (string, optional): default `animate-anyone-gen2`
51	- `image_url` (string, required)
52	- `template_id` (string, required)
53	- `use_ref_img_bg` (bool, optional): whether to keep the input image background
54
55	### Response
56	- `task_id` (string)
57	- `task_status` (string)
58	- `video_url` (string, when finished)
59
60	## Quick start
61
62	```bash
63	python skills/ai/video/aliyun-animate-anyone/scripts/prepare_animate_anyone_request.py \
64	--image-url "https://example.com/dancer.png" \
65	--template-id "tmpl_xxx" \
66	--use-ref-img-bg
67	```
68
69	## Operational guidance
70
71	- The action template must come from the official template-generation API.
72	- Full-body images work best when `use_ref_img_bg=false`; half-body images are not recommended in that mode.
73	- This skill is best for dancing or large body motion transfer, not generic talking-head tasks.
74
75	## Output location
76
77	- Default output: `output/aliyun-animate-anyone/request.json`
78	- Override base dir with `OUTPUT_DIR`.
79
80	## References
81
82	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-animate-anyone

397stars34forks

View on GitHub

How to install aliyun-animate-anyone?

cinience/alicloud-skills/aliyun-animate-anyone

$npx -y skills add cinience/alicloud-skills --skill aliyun-animate-anyone

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio AnimateAnyone
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-animate-anyone
9	python -m py_compile skills/ai/video/aliyun-animate-anyone/scripts/prepare_animate_anyone_request.py && echo "py_compile_ok" > output/aliyun-animate-anyone/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-animate-anyone/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, detection outputs, template IDs, and task polling snapshots under `output/aliyun-animate-anyone/`.
17	- Record whether the result should keep the reference image background or the source video background.
18
19	Use AnimateAnyone when the task needs motion transfer from a template video rather than plain talking-head animation.
20
21	## Critical model names
22
23	Use these exact model strings:
24	- `animate-anyone-detect-gen2`
25	- `animate-anyone-template-gen2`
26	- `animate-anyone-gen2`
27
28	Selection guidance:
29	- Run image detection first.
30	- Run template generation on the source motion video.
31	- Use `animate-anyone-gen2` for the final video job.
32
33	## Prerequisites
34
35	- China mainland (Beijing) only.
36	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
37	- Input files must be public HTTP/HTTPS URLs.
38
39	## Normalized interface (video.animate_anyone)
40
41	### Detect Request
42	- `model` (string, optional): default `animate-anyone-detect-gen2`
43	- `image_url` (string, required)
44
45	### Template Request
46	- `model` (string, optional): default `animate-anyone-template-gen2`
47	- `video_url` (string, required)
48
49	### Generate Request
50	- `model` (string, optional): default `animate-anyone-gen2`
51	- `image_url` (string, required)
52	- `template_id` (string, required)
53	- `use_ref_img_bg` (bool, optional): whether to keep the input image background
54
55	### Response
56	- `task_id` (string)
57	- `task_status` (string)
58	- `video_url` (string, when finished)
59
60	## Quick start
61
62	```bash
63	python skills/ai/video/aliyun-animate-anyone/scripts/prepare_animate_anyone_request.py \
64	--image-url "https://example.com/dancer.png" \
65	--template-id "tmpl_xxx" \
66	--use-ref-img-bg
67	```
68
69	## Operational guidance
70
71	- The action template must come from the official template-generation API.
72	- Full-body images work best when `use_ref_img_bg=false`; half-body images are not recommended in that mode.
73	- This skill is best for dancing or large body motion transfer, not generic talking-head tasks.
74
75	## Output location
76
77	- Default output: `output/aliyun-animate-anyone/request.json`
78	- Override base dir with `OUTPUT_DIR`.
79
80	## References
81
82	- `references/sources.md`

People who liked this also viewed

6 picks

Type