aliyun-happyhorse-r2v

Name: aliyun-happyhorse-r2v
Author: cinience

397stars34forks

How to install aliyun-happyhorse-r2v?

cinience/alicloud-skills/aliyun-happyhorse-r2v

$npx -y skills add cinience/alicloud-skills --skill aliyun-happyhorse-r2v

Installs into the current project.

Summary

Use when generating videos that fuse 1-9 reference images with DashScope HappyHorse 1.0 reference-to-video model (happyhorse-1.0-r2v). Use when implementing multi-subject reference-to-video synthesis where prompts cite the input images as character1..N via the video-synthesis asy

Files · 1

View on GitHub

SKILL.md

1	# HappyHorse 1.0 Reference-to-Video
2
3	## Validation
4
5	```bash
6	mkdir -p output/aliyun-happyhorse-r2v
7	python -m py_compile skills/ai/video/aliyun-happyhorse-r2v/scripts/r2v_happyhorse.py && echo "py_compile_ok" > output/aliyun-happyhorse-r2v/validate.txt
8	```
9
10	Pass criteria: command exits 0 and `output/aliyun-happyhorse-r2v/validate.txt` is generated.
11
12	## Output And Evidence
13
14	- Save task IDs, polling responses, and final video URLs to `output/aliyun-happyhorse-r2v/`.
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-r2v` — reference-to-video; 1-9 reference images fused into a single video, with `character1..N` references in the prompt
31
32	## Capabilities
33
34	\| Capability \| Description \| Required media \|
35	\|---\|---\|---\|
36	\| Reference-to-video \| Generate a video by fusing multiple subject/object reference images, guided by a prompt that references them as `character1`, `character2`, ... in input order \| 1-9 `reference_image` entries \|
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-r2v`
57	- `input.prompt` (string, required) — up to 5000 non-CJK / 2500 CJK characters; reference subjects via `character1`, `character2`, ... matching `media` array order
58	- `input.media` (array, required) — 1 to 9 elements, each:
59	- `type`: `reference_image`
60	- `url`: public HTTP/HTTPS URL of a reference image
61	- `parameters.resolution` (string, optional) — `720P` or `1080P` (default: `1080P`)
62	- `parameters.ratio` (string, optional) — `16:9` (default), `9:16`, `1:1`, `4:3`, `3:4`
63	- `parameters.duration` (integer, optional) — video length in seconds, range [3, 15] (default: 5)
64	- `parameters.watermark` (boolean, optional) — bottom-right "Happy Horse" watermark (default: `true`)
65	- `parameters.seed` (integer, optional) — range [0, 2147483647]
66
67	### Media input limits
68
69	Reference image (`type=reference_image`):
70	- Formats: JPEG, JPG, PNG, WEBP
71	- Resolution: short side ≥ 400 pixels (720P or higher recommended)
72	- Max size: 10 MB per image
73	- Avoid blurry, over-compressed, or very small images
74
75	### Character indexing rule
76
77	The first `reference_image` in the `media` array maps to `character1`, the second to `character2`, and so on up to `character9`. Reorder the array if you want a specific reference to bind to a specific `characterN`.
78
79	### Response (task creation)
80	- `output.task_id` (string) — valid 24 hours
81	- `output.task_status` (string) — `PENDING` \| `RUNNING` \| `SUCCEEDED` \| `FAILED` \| `CANCELED` \| `UNKNOWN`
82	- `request_id` (string)
83
84	### Response (task result, on SUCCEEDED)
85	- `output.video_url` (string) — generated MP4 (H.264) URL, valid 24 hours
86	- `output.orig_prompt` (string)
87	- `output.submit_time` / `output.scheduled_time` / `output.end_time` (string)
88	- `usage.duration` (integer) — billable duration in seconds
89	- `usage.output_video_duration` (integer)
90	- `usage.input_video_duration` (integer) — fixed 0 for r2v
91	- `usage.SR` (integer) — output resolution tier
92	- `usage.ratio` (string)
93	- `usage.video_count` (integer) — fixed 1
94
95	## Quick start (Python + HTTP)
96
97	```python
98	import os
99	import time
100	import requests
101
102	API_KEY = os.getenv("DASHSCOPE_API_KEY")
103	BASE_URL = "https://dashscope.aliyuncs.com/api/v1"
104
105
106	def create_r2v_task(req: dict) -> str:
107	"""Create a reference-to-video task and return task_id."""
108	refs = req["reference_images"]
109	if not 1 <= len(refs) <= 9:
110	raise ValueError("Need 1-9 reference images")
111	payload = {
112	"model": "happyhorse-1.0-r2v",
113	"input": {
114	"prompt": req["prompt"],
115	"media": [{"type": "reference_image", "url": u} for u in refs],
116	},
117	"parameters": {
118	"resolution": req.get("resolution", "1080P"),
119	"ratio": req.get("ratio", "16:9"),
120	"duration": req.get("duration", 5),
121	"watermark": req.get("watermark", True),
122	},
123	}
124	if req.get("seed") is not None:
125	payload["parameters"]["seed

People who liked this also viewed

6 picks

Type

aliyun-happyhorse-r2v

397stars34forks

View on GitHub

How to install aliyun-happyhorse-r2v?

cinience/alicloud-skills/aliyun-happyhorse-r2v

$npx -y skills add cinience/alicloud-skills --skill aliyun-happyhorse-r2v

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# HappyHorse 1.0 Reference-to-Video
2
3	## Validation
4
5	```bash
6	mkdir -p output/aliyun-happyhorse-r2v
7	python -m py_compile skills/ai/video/aliyun-happyhorse-r2v/scripts/r2v_happyhorse.py && echo "py_compile_ok" > output/aliyun-happyhorse-r2v/validate.txt
8	```
9
10	Pass criteria: command exits 0 and `output/aliyun-happyhorse-r2v/validate.txt` is generated.
11
12	## Output And Evidence
13
14	- Save task IDs, polling responses, and final video URLs to `output/aliyun-happyhorse-r2v/`.
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-r2v` — reference-to-video; 1-9 reference images fused into a single video, with `character1..N` references in the prompt
31
32	## Capabilities
33
34	\| Capability \| Description \| Required media \|
35	\|---\|---\|---\|
36	\| Reference-to-video \| Generate a video by fusing multiple subject/object reference images, guided by a prompt that references them as `character1`, `character2`, ... in input order \| 1-9 `reference_image` entries \|
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-r2v`
57	- `input.prompt` (string, required) — up to 5000 non-CJK / 2500 CJK characters; reference subjects via `character1`, `character2`, ... matching `media` array order
58	- `input.media` (array, required) — 1 to 9 elements, each:
59	- `type`: `reference_image`
60	- `url`: public HTTP/HTTPS URL of a reference image
61	- `parameters.resolution` (string, optional) — `720P` or `1080P` (default: `1080P`)
62	- `parameters.ratio` (string, optional) — `16:9` (default), `9:16`, `1:1`, `4:3`, `3:4`
63	- `parameters.duration` (integer, optional) — video length in seconds, range [3, 15] (default: 5)
64	- `parameters.watermark` (boolean, optional) — bottom-right "Happy Horse" watermark (default: `true`)
65	- `parameters.seed` (integer, optional) — range [0, 2147483647]
66
67	### Media input limits
68
69	Reference image (`type=reference_image`):
70	- Formats: JPEG, JPG, PNG, WEBP
71	- Resolution: short side ≥ 400 pixels (720P or higher recommended)
72	- Max size: 10 MB per image
73	- Avoid blurry, over-compressed, or very small images
74
75	### Character indexing rule
76
77	The first `reference_image` in the `media` array maps to `character1`, the second to `character2`, and so on up to `character9`. Reorder the array if you want a specific reference to bind to a specific `characterN`.
78
79	### Response (task creation)
80	- `output.task_id` (string) — valid 24 hours
81	- `output.task_status` (string) — `PENDING` \| `RUNNING` \| `SUCCEEDED` \| `FAILED` \| `CANCELED` \| `UNKNOWN`
82	- `request_id` (string)
83
84	### Response (task result, on SUCCEEDED)
85	- `output.video_url` (string) — generated MP4 (H.264) URL, valid 24 hours
86	- `output.orig_prompt` (string)
87	- `output.submit_time` / `output.scheduled_time` / `output.end_time` (string)
88	- `usage.duration` (integer) — billable duration in seconds
89	- `usage.output_video_duration` (integer)
90	- `usage.input_video_duration` (integer) — fixed 0 for r2v
91	- `usage.SR` (integer) — output resolution tier
92	- `usage.ratio` (string)
93	- `usage.video_count` (integer) — fixed 1
94
95	## Quick start (Python + HTTP)
96
97	```python
98	import os
99	import time
100	import requests
101
102	API_KEY = os.getenv("DASHSCOPE_API_KEY")
103	BASE_URL = "https://dashscope.aliyuncs.com/api/v1"
104
105
106	def create_r2v_task(req: dict) -> str:
107	"""Create a reference-to-video task and return task_id."""
108	refs = req["reference_images"]
109	if not 1 <= len(refs) <= 9:
110	raise ValueError("Need 1-9 reference images")
111	payload = {
112	"model": "happyhorse-1.0-r2v",
113	"input": {
114	"prompt": req["prompt"],
115	"media": [{"type": "reference_image", "url": u} for u in refs],
116	},
117	"parameters": {
118	"resolution": req.get("resolution", "1080P"),
119	"ratio": req.get("ratio", "16:9"),
120	"duration": req.get("duration", 5),
121	"watermark": req.get("watermark", True),
122	},
123	}
124	if req.get("seed") is not None:
125	payload["parameters"]["seed

People who liked this also viewed

6 picks

Type