aliyun-emo

Name: aliyun-emo
Author: cinience

397stars34forks

How to install aliyun-emo?

cinience/alicloud-skills/aliyun-emo

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

Installs into the current project.

Summary

Use when generating expressive portrait videos from a person image and speech audio with Alibaba Cloud Model Studio EMO (emo-v1). Use when creating non-Wan avatar clips with stronger expression style control from a detected portrait image.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio EMO
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-emo
9	python -m py_compile skills/ai/video/aliyun-emo/scripts/prepare_emo_request.py && echo "py_compile_ok" > output/aliyun-emo/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-emo/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, detection boxes, and task polling snapshots under `output/aliyun-emo/`.
17	- Record the chosen `style_level` and the exact `face_bbox` / `ext_bbox`.
18
19	Use EMO when the input is a portrait image and speech audio, and you need a non-Wan expressive talking-head result.
20
21	## Critical model names
22
23	Use these exact model strings:
24	- `emo-v1-detect`
25	- `emo-v1`
26
27	Selection guidance:
28	- Run image detection first to obtain `face_bbox` and `ext_bbox`.
29	- Use `emo-v1` only after detection succeeds.
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 files must be public HTTP/HTTPS URLs.
36
37	## Normalized interface (video.emo)
38
39	### Detect Request
40	- `model` (string, optional): default `emo-v1-detect`
41	- `image_url` (string, required)
42
43	### Generate Request
44	- `model` (string, optional): default `emo-v1`
45	- `image_url` (string, required)
46	- `audio_url` (string, required)
47	- `face_bbox` (array<int>, required)
48	- `ext_bbox` (array<int>, required)
49	- `style_level` (string, optional): `normal`, `calm`, or `active`
50
51	### Response
52	- `task_id` (string)
53	- `task_status` (string)
54	- `video_url` (string, when finished)
55
56	## Quick start
57
58	```bash
59	python skills/ai/video/aliyun-emo/scripts/prepare_emo_request.py \
60	--image-url "https://example.com/portrait.png" \
61	--audio-url "https://example.com/speech.mp3" \
62	--face-bbox 302,286,610,593 \
63	--ext-bbox 71,9,840,778 \
64	--style-level active
65	```
66
67	## Operational guidance
68
69	- Do not invent `face_bbox` or `ext_bbox`; use the detection API output.
70	- `ext_bbox` ratio determines output format: `1:1` yields `512x512`, `3:4` yields `512x704`.
71	- Keep the input portrait clear and front-facing for better expression quality.
72	- EMO is portrait-focused; for full-scene human videos use other skills instead.
73
74	## Output location
75
76	- Default output: `output/aliyun-emo/request.json`
77	- Override base dir with `OUTPUT_DIR`.
78
79	## References
80
81	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-emo

397stars34forks

View on GitHub

How to install aliyun-emo?

cinience/alicloud-skills/aliyun-emo

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio EMO
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-emo
9	python -m py_compile skills/ai/video/aliyun-emo/scripts/prepare_emo_request.py && echo "py_compile_ok" > output/aliyun-emo/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-emo/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, detection boxes, and task polling snapshots under `output/aliyun-emo/`.
17	- Record the chosen `style_level` and the exact `face_bbox` / `ext_bbox`.
18
19	Use EMO when the input is a portrait image and speech audio, and you need a non-Wan expressive talking-head result.
20
21	## Critical model names
22
23	Use these exact model strings:
24	- `emo-v1-detect`
25	- `emo-v1`
26
27	Selection guidance:
28	- Run image detection first to obtain `face_bbox` and `ext_bbox`.
29	- Use `emo-v1` only after detection succeeds.
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 files must be public HTTP/HTTPS URLs.
36
37	## Normalized interface (video.emo)
38
39	### Detect Request
40	- `model` (string, optional): default `emo-v1-detect`
41	- `image_url` (string, required)
42
43	### Generate Request
44	- `model` (string, optional): default `emo-v1`
45	- `image_url` (string, required)
46	- `audio_url` (string, required)
47	- `face_bbox` (array<int>, required)
48	- `ext_bbox` (array<int>, required)
49	- `style_level` (string, optional): `normal`, `calm`, or `active`
50
51	### Response
52	- `task_id` (string)
53	- `task_status` (string)
54	- `video_url` (string, when finished)
55
56	## Quick start
57
58	```bash
59	python skills/ai/video/aliyun-emo/scripts/prepare_emo_request.py \
60	--image-url "https://example.com/portrait.png" \
61	--audio-url "https://example.com/speech.mp3" \
62	--face-bbox 302,286,610,593 \
63	--ext-bbox 71,9,840,778 \
64	--style-level active
65	```
66
67	## Operational guidance
68
69	- Do not invent `face_bbox` or `ext_bbox`; use the detection API output.
70	- `ext_bbox` ratio determines output format: `1:1` yields `512x512`, `3:4` yields `512x704`.
71	- Keep the input portrait clear and front-facing for better expression quality.
72	- EMO is portrait-focused; for full-scene human videos use other skills instead.
73
74	## Output location
75
76	- Default output: `output/aliyun-emo/request.json`
77	- Override base dir with `OUTPUT_DIR`.
78
79	## References
80
81	- `references/sources.md`

People who liked this also viewed

6 picks

Type