aliyun-happyhorse-i2v

Name: aliyun-happyhorse-i2v
Author: cinience

397stars34forks

How to install aliyun-happyhorse-i2v?

cinience/alicloud-skills/aliyun-happyhorse-i2v

$npx -y skills add cinience/alicloud-skills --skill aliyun-happyhorse-i2v

Installs into the current project.

Summary

Use when generating videos from a single first-frame image with DashScope HappyHorse 1.0 image-to-video model (happyhorse-1.0-i2v). Use when implementing first-frame video generation with optional text guidance via the video-synthesis async API on Alibaba Cloud Model Studio.

Files · 1

View on GitHub

SKILL.md

1	# HappyHorse 1.0 Image-to-Video (First Frame)
2
3	## Validation
4
5	```bash
6	mkdir -p output/aliyun-happyhorse-i2v
7	python -m py_compile skills/ai/video/aliyun-happyhorse-i2v/scripts/i2v_happyhorse.py && echo "py_compile_ok" > output/aliyun-happyhorse-i2v/validate.txt
8	```
9
10	Pass criteria: command exits 0 and `output/aliyun-happyhorse-i2v/validate.txt` is generated.
11
12	## Output And Evidence
13
14	- Save task IDs, polling responses, and final video URLs to `output/aliyun-happyhorse-i2v/`.
15	- Keep at least one end-to-end run log for troubleshooting.
16
17	## Prerequisites
18
19	- Install dependencies (recommended in a venv):
20
21	```bash
22	python3 -m venv .venv
23	. .venv/bin/activate
24	python -m pip install requests
25	```
26	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
27
28	## Critical model names
29
30	- `happyhorse-1.0-i2v` — first-frame image-to-video; output aspect ratio follows the input image automatically
31
32	## Capabilities
33
34	\| Capability \| Description \| Required media \|
35	\|---\|---\|---\|
36	\| First-frame video \| Generate a video from one first-frame image, optionally guided by a text prompt \| `first_frame` (exactly 1) \|
37
38	## API endpoint (async only)
39
40	```
41	POST https://dashscope.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis
42	```
43
44	Required headers:
45	- `Authorization: Bearer $DASHSCOPE_API_KEY`
46	- `Content-Type: application/json`
47	- `X-DashScope-Async: enable`
48
49	Singapore endpoint: replace `dashscope.aliyuncs.com` with `dashscope-intl.aliyuncs.com`.
50
51	Polling endpoint: `GET https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}` — recommended interval 15s.
52
53	## Normalized interface
54
55	### Request
56	- `model` (string, required) — fixed `happyhorse-1.0-i2v`
57	- `input.prompt` (string, optional) — up to 5000 non-CJK / 2500 CJK characters
58	- `input.media` (array, required) — exactly one element with:
59	- `type`: `first_frame`
60	- `url`: public HTTP/HTTPS URL of the first-frame image
61	- `parameters.resolution` (string, optional) — `720P` or `1080P` (default: `1080P`)
62	- `parameters.duration` (integer, optional) — video length in seconds, range [3, 15] (default: 5)
63	- `parameters.watermark` (boolean, optional) — bottom-right "Happy Horse" watermark (default: `true`)
64	- `parameters.seed` (integer, optional) — range [0, 2147483647]
65
66	The output video aspect ratio follows the input first-frame image; `ratio` is not supported for i2v.
67
68	### Media input limits
69
70	First-frame image (`type=first_frame`):
71	- Formats: JPEG, JPG, PNG, WEBP
72	- Resolution: width and height ≥ 300 pixels
73	- Aspect ratio: 1:2.5 ~ 2.5:1
74	- Max size: 10 MB
75
76	### Response (task creation)
77	- `output.task_id` (string) — valid 24 hours
78	- `output.task_status` (string) — `PENDING` \| `RUNNING` \| `SUCCEEDED` \| `FAILED` \| `CANCELED` \| `UNKNOWN`
79	- `request_id` (string)
80
81	### Response (task result, on SUCCEEDED)
82	- `output.video_url` (string) — generated MP4 (H.264, 24fps) URL, valid 24 hours
83	- `output.orig_prompt` (string)
84	- `output.submit_time` / `output.scheduled_time` / `output.end_time` (string)
85	- `usage.duration` (integer) — billable duration in seconds
86	- `usage.output_video_duration` (integer)
87	- `usage.input_video_duration` (integer) — fixed 0 for i2v
88	- `usage.SR` (integer) — output resolution tier
89	- `usage.video_count` (integer) — fixed 1
90
91	## Quick start (Python + HTTP)
92
93	```python
94	import os
95	import time
96	import requests
97
98	API_KEY = os.getenv("DASHSCOPE_API_KEY")
99	BASE_URL = "https://dashscope.aliyuncs.com/api/v1"
100
101
102	def create_i2v_task(req: dict) -> str:
103	"""Create an image-to-video task and return task_id."""
104	payload = {
105	"model": "happyhorse-1.0-i2v",
106	"input": {
107	"prompt": req.get("prompt", ""),
108	"media": [{"type": "first_frame", "url": req["first_frame_url"]}],
109	},
110	"parameters": {
111	"resolution": req.get("resolution", "1080P"),
112	"duration": req.get("duration", 5),
113	"watermark": req.get("watermark", True),
114	},
115	}
116	if req.get("seed") is not None:
117	payload["parameters"]["seed"] = req["seed"]
118
119	resp = requests.post(
120	f"{BASE_URL}/services/aigc/video-generation/video-synthesis",
121	headers={
122	"Authorization": f"Bearer {API_KEY}",
123	"Content-Type": "application/json",
124	"X-DashScope-Async": "enable",
125	},
126	json=payload,
127	)
128	resp.raise_for_status()
129	return resp.json()["output"]["task_id"]
130
131
132	def poll_task(task_id: str, interval: int = 15) -> dict:
133	while True:
134	resp = requests.get(
135	f"{BASE_URL}/tasks/{task_id}",
136	headers={"Authorization": f"Bearer {API_KEY}"},
137	)
138	resp.raise_for_status()
139	data = resp.json()

People who liked this also viewed

6 picks

Type

aliyun-happyhorse-i2v

397stars34forks

View on GitHub

How to install aliyun-happyhorse-i2v?

cinience/alicloud-skills/aliyun-happyhorse-i2v

$npx -y skills add cinience/alicloud-skills --skill aliyun-happyhorse-i2v

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# HappyHorse 1.0 Image-to-Video (First Frame)
2
3	## Validation
4
5	```bash
6	mkdir -p output/aliyun-happyhorse-i2v
7	python -m py_compile skills/ai/video/aliyun-happyhorse-i2v/scripts/i2v_happyhorse.py && echo "py_compile_ok" > output/aliyun-happyhorse-i2v/validate.txt
8	```
9
10	Pass criteria: command exits 0 and `output/aliyun-happyhorse-i2v/validate.txt` is generated.
11
12	## Output And Evidence
13
14	- Save task IDs, polling responses, and final video URLs to `output/aliyun-happyhorse-i2v/`.
15	- Keep at least one end-to-end run log for troubleshooting.
16
17	## Prerequisites
18
19	- Install dependencies (recommended in a venv):
20
21	```bash
22	python3 -m venv .venv
23	. .venv/bin/activate
24	python -m pip install requests
25	```
26	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
27
28	## Critical model names
29
30	- `happyhorse-1.0-i2v` — first-frame image-to-video; output aspect ratio follows the input image automatically
31
32	## Capabilities
33
34	\| Capability \| Description \| Required media \|
35	\|---\|---\|---\|
36	\| First-frame video \| Generate a video from one first-frame image, optionally guided by a text prompt \| `first_frame` (exactly 1) \|
37
38	## API endpoint (async only)
39
40	```
41	POST https://dashscope.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis
42	```
43
44	Required headers:
45	- `Authorization: Bearer $DASHSCOPE_API_KEY`
46	- `Content-Type: application/json`
47	- `X-DashScope-Async: enable`
48
49	Singapore endpoint: replace `dashscope.aliyuncs.com` with `dashscope-intl.aliyuncs.com`.
50
51	Polling endpoint: `GET https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}` — recommended interval 15s.
52
53	## Normalized interface
54
55	### Request
56	- `model` (string, required) — fixed `happyhorse-1.0-i2v`
57	- `input.prompt` (string, optional) — up to 5000 non-CJK / 2500 CJK characters
58	- `input.media` (array, required) — exactly one element with:
59	- `type`: `first_frame`
60	- `url`: public HTTP/HTTPS URL of the first-frame image
61	- `parameters.resolution` (string, optional) — `720P` or `1080P` (default: `1080P`)
62	- `parameters.duration` (integer, optional) — video length in seconds, range [3, 15] (default: 5)
63	- `parameters.watermark` (boolean, optional) — bottom-right "Happy Horse" watermark (default: `true`)
64	- `parameters.seed` (integer, optional) — range [0, 2147483647]
65
66	The output video aspect ratio follows the input first-frame image; `ratio` is not supported for i2v.
67
68	### Media input limits
69
70	First-frame image (`type=first_frame`):
71	- Formats: JPEG, JPG, PNG, WEBP
72	- Resolution: width and height ≥ 300 pixels
73	- Aspect ratio: 1:2.5 ~ 2.5:1
74	- Max size: 10 MB
75
76	### Response (task creation)
77	- `output.task_id` (string) — valid 24 hours
78	- `output.task_status` (string) — `PENDING` \| `RUNNING` \| `SUCCEEDED` \| `FAILED` \| `CANCELED` \| `UNKNOWN`
79	- `request_id` (string)
80
81	### Response (task result, on SUCCEEDED)
82	- `output.video_url` (string) — generated MP4 (H.264, 24fps) URL, valid 24 hours
83	- `output.orig_prompt` (string)
84	- `output.submit_time` / `output.scheduled_time` / `output.end_time` (string)
85	- `usage.duration` (integer) — billable duration in seconds
86	- `usage.output_video_duration` (integer)
87	- `usage.input_video_duration` (integer) — fixed 0 for i2v
88	- `usage.SR` (integer) — output resolution tier
89	- `usage.video_count` (integer) — fixed 1
90
91	## Quick start (Python + HTTP)
92
93	```python
94	import os
95	import time
96	import requests
97
98	API_KEY = os.getenv("DASHSCOPE_API_KEY")
99	BASE_URL = "https://dashscope.aliyuncs.com/api/v1"
100
101
102	def create_i2v_task(req: dict) -> str:
103	"""Create an image-to-video task and return task_id."""
104	payload = {
105	"model": "happyhorse-1.0-i2v",
106	"input": {
107	"prompt": req.get("prompt", ""),
108	"media": [{"type": "first_frame", "url": req["first_frame_url"]}],
109	},
110	"parameters": {
111	"resolution": req.get("resolution", "1080P"),
112	"duration": req.get("duration", 5),
113	"watermark": req.get("watermark", True),
114	},
115	}
116	if req.get("seed") is not None:
117	payload["parameters"]["seed"] = req["seed"]
118
119	resp = requests.post(
120	f"{BASE_URL}/services/aigc/video-generation/video-synthesis",
121	headers={
122	"Authorization": f"Bearer {API_KEY}",
123	"Content-Type": "application/json",
124	"X-DashScope-Async": "enable",
125	},
126	json=payload,
127	)
128	resp.raise_for_status()
129	return resp.json()["output"]["task_id"]
130
131
132	def poll_task(task_id: str, interval: int = 15) -> dict:
133	while True:
134	resp = requests.get(
135	f"{BASE_URL}/tasks/{task_id}",
136	headers={"Authorization": f"Bearer {API_KEY}"},
137	)
138	resp.raise_for_status()
139	data = resp.json()

People who liked this also viewed

6 picks

Type