aliyun-happyhorse-t2v

Name: aliyun-happyhorse-t2v
Author: cinience

397stars34forks

How to install aliyun-happyhorse-t2v?

cinience/alicloud-skills/aliyun-happyhorse-t2v

$npx -y skills add cinience/alicloud-skills --skill aliyun-happyhorse-t2v

Installs into the current project.

Summary

Use when generating videos from text prompts with DashScope HappyHorse 1.0 text-to-video model (happyhorse-1.0-t2v). Use when implementing pure text-to-video synthesis via the video-synthesis async API on Alibaba Cloud Model Studio.

Files · 1

View on GitHub

SKILL.md

1	# HappyHorse 1.0 Text-to-Video
2
3	## Validation
4
5	```bash
6	mkdir -p output/aliyun-happyhorse-t2v
7	python -m py_compile skills/ai/video/aliyun-happyhorse-t2v/scripts/t2v_happyhorse.py && echo "py_compile_ok" > output/aliyun-happyhorse-t2v/validate.txt
8	```
9
10	Pass criteria: command exits 0 and `output/aliyun-happyhorse-t2v/validate.txt` is generated.
11
12	## Output And Evidence
13
14	- Save task IDs, polling responses, and final video URLs to `output/aliyun-happyhorse-t2v/`.
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-t2v` — text-to-video, supports resolution, ratio, duration, watermark and seed control
31
32	## Capabilities
33
34	\| Capability \| Description \| Required input \|
35	\|---\|---\|---\|
36	\| Text-to-video \| Generate a physically realistic video from a text prompt only \| `prompt` \|
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-t2v`
57	- `input.prompt` (string, required) — up to 5000 non-CJK characters or 2500 CJK characters; longer is truncated
58	- `parameters.resolution` (string, optional) — `720P` or `1080P` (default: `1080P`)
59	- `parameters.ratio` (string, optional) — `16:9` (default), `9:16`, `1:1`, `4:3`, `3:4`
60	- `parameters.duration` (integer, optional) — video length in seconds, range [3, 15] (default: 5)
61	- `parameters.watermark` (boolean, optional) — add bottom-right "Happy Horse" watermark (default: `true`)
62	- `parameters.seed` (integer, optional) — range [0, 2147483647]
63
64	### Response (task creation)
65	- `output.task_id` (string) — use for polling, valid 24 hours
66	- `output.task_status` (string) — `PENDING` \| `RUNNING` \| `SUCCEEDED` \| `FAILED` \| `CANCELED` \| `UNKNOWN`
67	- `request_id` (string)
68
69	### Response (task result, on SUCCEEDED)
70	- `output.video_url` (string) — generated MP4 (H.264) URL, valid 24 hours
71	- `output.orig_prompt` (string)
72	- `output.submit_time` / `output.scheduled_time` / `output.end_time` (string)
73	- `usage.duration` (integer) — billable duration in seconds
74	- `usage.output_video_duration` (integer)
75	- `usage.SR` (integer) — output resolution tier
76	- `usage.ratio` (string)
77	- `usage.video_count` (integer) — fixed 1
78
79	## Quick start (Python + HTTP)
80
81	```python
82	import os
83	import time
84	import requests
85
86	API_KEY = os.getenv("DASHSCOPE_API_KEY")
87	BASE_URL = "https://dashscope.aliyuncs.com/api/v1"
88
89
90	def create_t2v_task(req: dict) -> str:
91	"""Create a text-to-video task and return task_id."""
92	payload = {
93	"model": "happyhorse-1.0-t2v",
94	"input": {"prompt": req["prompt"]},
95	"parameters": {
96	"resolution": req.get("resolution", "1080P"),
97	"ratio": req.get("ratio", "16:9"),
98	"duration": req.get("duration", 5),
99	"watermark": req.get("watermark", True),
100	},
101	}
102	if req.get("seed") is not None:
103	payload["parameters"]["seed"] = req["seed"]
104
105	resp = requests.post(
106	f"{BASE_URL}/services/aigc/video-generation/video-synthesis",
107	headers={
108	"Authorization": f"Bearer {API_KEY}",
109	"Content-Type": "application/json",
110	"X-DashScope-Async": "enable",
111	},
112	json=payload,
113	)
114	resp.raise_for_status()
115	return resp.json()["output"]["task_id"]
116
117
118	def poll_task(task_id: str, interval: int = 15) -> dict:
119	while True:
120	resp = requests.get(
121	f"{BASE_URL}/tasks/{task_id}",
122	headers={"Authorization": f"Bearer {API_KEY}"},
123	)
124	resp.raise_for_status()
125	data = resp.json()
126	if data["output"]["task_status"] in ("SUCCEEDED", "FAILED", "CANCELED"):
127	return data
128	time.sleep(interval)
129	```
130
131	## Usage examples
132
133	```python
134	# Minimal — pure text prompt
135	task_id = create_t2v_task({
136	"prompt": "一座由硬纸板和瓶盖搭建的微型城市，在夜晚焕发出生机。",
137	"duration": 5,
138	})
139
140	# Vertical short video at 720P
141	task_id = create_t2v_task({
142	"prompt": "A neon cyberpunk alley at midnight, rain reflections, slow dolly forward.",
143	"resolution": "720P",
144	"ratio": "9:16",
145	"duration": 8,
146	})
147	``

People who liked this also viewed

6 picks

Type

aliyun-happyhorse-t2v

397stars34forks

View on GitHub

How to install aliyun-happyhorse-t2v?

cinience/alicloud-skills/aliyun-happyhorse-t2v

$npx -y skills add cinience/alicloud-skills --skill aliyun-happyhorse-t2v

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# HappyHorse 1.0 Text-to-Video
2
3	## Validation
4
5	```bash
6	mkdir -p output/aliyun-happyhorse-t2v
7	python -m py_compile skills/ai/video/aliyun-happyhorse-t2v/scripts/t2v_happyhorse.py && echo "py_compile_ok" > output/aliyun-happyhorse-t2v/validate.txt
8	```
9
10	Pass criteria: command exits 0 and `output/aliyun-happyhorse-t2v/validate.txt` is generated.
11
12	## Output And Evidence
13
14	- Save task IDs, polling responses, and final video URLs to `output/aliyun-happyhorse-t2v/`.
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-t2v` — text-to-video, supports resolution, ratio, duration, watermark and seed control
31
32	## Capabilities
33
34	\| Capability \| Description \| Required input \|
35	\|---\|---\|---\|
36	\| Text-to-video \| Generate a physically realistic video from a text prompt only \| `prompt` \|
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-t2v`
57	- `input.prompt` (string, required) — up to 5000 non-CJK characters or 2500 CJK characters; longer is truncated
58	- `parameters.resolution` (string, optional) — `720P` or `1080P` (default: `1080P`)
59	- `parameters.ratio` (string, optional) — `16:9` (default), `9:16`, `1:1`, `4:3`, `3:4`
60	- `parameters.duration` (integer, optional) — video length in seconds, range [3, 15] (default: 5)
61	- `parameters.watermark` (boolean, optional) — add bottom-right "Happy Horse" watermark (default: `true`)
62	- `parameters.seed` (integer, optional) — range [0, 2147483647]
63
64	### Response (task creation)
65	- `output.task_id` (string) — use for polling, valid 24 hours
66	- `output.task_status` (string) — `PENDING` \| `RUNNING` \| `SUCCEEDED` \| `FAILED` \| `CANCELED` \| `UNKNOWN`
67	- `request_id` (string)
68
69	### Response (task result, on SUCCEEDED)
70	- `output.video_url` (string) — generated MP4 (H.264) URL, valid 24 hours
71	- `output.orig_prompt` (string)
72	- `output.submit_time` / `output.scheduled_time` / `output.end_time` (string)
73	- `usage.duration` (integer) — billable duration in seconds
74	- `usage.output_video_duration` (integer)
75	- `usage.SR` (integer) — output resolution tier
76	- `usage.ratio` (string)
77	- `usage.video_count` (integer) — fixed 1
78
79	## Quick start (Python + HTTP)
80
81	```python
82	import os
83	import time
84	import requests
85
86	API_KEY = os.getenv("DASHSCOPE_API_KEY")
87	BASE_URL = "https://dashscope.aliyuncs.com/api/v1"
88
89
90	def create_t2v_task(req: dict) -> str:
91	"""Create a text-to-video task and return task_id."""
92	payload = {
93	"model": "happyhorse-1.0-t2v",
94	"input": {"prompt": req["prompt"]},
95	"parameters": {
96	"resolution": req.get("resolution", "1080P"),
97	"ratio": req.get("ratio", "16:9"),
98	"duration": req.get("duration", 5),
99	"watermark": req.get("watermark", True),
100	},
101	}
102	if req.get("seed") is not None:
103	payload["parameters"]["seed"] = req["seed"]
104
105	resp = requests.post(
106	f"{BASE_URL}/services/aigc/video-generation/video-synthesis",
107	headers={
108	"Authorization": f"Bearer {API_KEY}",
109	"Content-Type": "application/json",
110	"X-DashScope-Async": "enable",
111	},
112	json=payload,
113	)
114	resp.raise_for_status()
115	return resp.json()["output"]["task_id"]
116
117
118	def poll_task(task_id: str, interval: int = 15) -> dict:
119	while True:
120	resp = requests.get(
121	f"{BASE_URL}/tasks/{task_id}",
122	headers={"Authorization": f"Bearer {API_KEY}"},
123	)
124	resp.raise_for_status()
125	data = resp.json()
126	if data["output"]["task_status"] in ("SUCCEEDED", "FAILED", "CANCELED"):
127	return data
128	time.sleep(interval)
129	```
130
131	## Usage examples
132
133	```python
134	# Minimal — pure text prompt
135	task_id = create_t2v_task({
136	"prompt": "一座由硬纸板和瓶盖搭建的微型城市，在夜晚焕发出生机。",
137	"duration": 5,
138	})
139
140	# Vertical short video at 720P
141	task_id = create_t2v_task({
142	"prompt": "A neon cyberpunk alley at midnight, rain reflections, slow dolly forward.",
143	"resolution": "720P",
144	"ratio": "9:16",
145	"duration": 8,
146	})
147	``

People who liked this also viewed

6 picks

Type