aliyun-happyhorse-r2v
This skill generates videos by blending multiple reference images into a single output, with prompts that map each image to a character placeholder (character1, character2, etc.). Supports 1–9 images per video, customizable resolution, aspect ratio, and duration via the DashScope async API.
aliyun-happyhorse-r2v generates videos by fusing 1-9 reference images with character-mapped prompts via DashScope.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-18
aliyun-happyhorse-r2v generates videos by fusing 1-9 reference images with character-mapped prompts via DashScope. This skill generates videos by blending multiple reference images into a single output, with prompts that map each image to a character placeholder (character1, character2, etc.). Supports 1–9 images per video, customizable resolution, aspect ratio, and duration via the DashScope async API.
Use it when
- Yes.
- aliyun-happyhorse-r2v implements async reference-to-video synthesis via the DashScope HappyHorse API.
Verify before relying
Read SKILL.md below before installing (4 files). Open directory: indexed for reading, not audited.
Install
cinience/alicloud-skills/aliyun-happyhorse-r2v · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I generate video from reference images using aliyun-happyhorse-r2v?
aliyun-happyhorse-r2v generates videos by fusing 1–9 reference images into a single output video. You provide the images and a text prompt that maps each image to a character placeholder (character1, character2, etc.). The skill uses the DashScope HappyHorse API to process your request asynchronously, then polls and retrieves the completed video. Customize resolution, aspect ratio, and duration as needed.
Can aliyun-happyhorse-r2v create multi-subject video animations?
Yes. aliyun-happyhorse-r2v supports multi-subject video synthesis by binding multiple character references to images in your generation prompts. You can fuse up to 9 reference images into a single video, with each image mapped to a character placeholder in your prompt text, enabling rich multi-character animations.
What is the DashScope r2v video generation workflow?
aliyun-happyhorse-r2v implements async reference-to-video synthesis via the DashScope HappyHorse API. You submit reference images and a character-mapped prompt; the API processes the request asynchronously. The skill then polls the task status and retrieves your generated video once complete, handling the full async lifecycle for you.
How many reference images can aliyun-happyhorse-r2v fuse into one video?
aliyun-happyhorse-r2v supports fusing 1 to 9 reference images per video generation. Each image is bound to a character placeholder in your prompt (character1, character2, etc.), allowing flexible multi-subject compositions within that range.
What customization options does aliyun-happyhorse-r2v offer?
aliyun-happyhorse-r2v lets you customize resolution, aspect ratio, and duration for your generated videos. These settings apply across the reference-to-video synthesis process, giving you control over output format and length alongside your character-mapped prompt guidance.
Is aliyun-happyhorse-r2v open source?
Yes, aliyun-happyhorse-r2v is released under the MIT license, making it open source and freely available for use, modification, and distribution.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
HappyHorse 1.0 Reference-to-Video
Validation
mkdir -p output/aliyun-happyhorse-r2v
python -m py_compile skills/ai/video/aliyun-happyhorse-r2v/scripts/r2v_happyhorse.py && echo "py_compile_ok" > output/aliyun-happyhorse-r2v/validate.txt
Pass criteria: command exits 0 and output/aliyun-happyhorse-r2v/validate.txt is generated.
Output And Evidence
- Save task IDs, polling responses, and final video URLs to
output/aliyun-happyhorse-r2v/. - Keep at least one end-to-end run log for troubleshooting.
Prerequisites
- Install dependencies (recommended in a venv):
python3 -m venv .venv
. .venv/bin/activate
python -m pip install requests
- Set
DASHSCOPE_API_KEYin your environment, or adddashscope_api_keyto~/.alibabacloud/credentials.
Critical model names
happyhorse-1.0-r2v— reference-to-video;
(truncated - see the full file via the links below)
File tree — 4 files
skills/ai/video/aliyun-happyhorse-r2v/SKILL.md
skills/ai/video/aliyun-happyhorse-r2v/references/api_reference.md
skills/ai/video/aliyun-happyhorse-r2v/references/sources.md
skills/ai/video/aliyun-happyhorse-r2v/scripts/r2v_happyhorse.py
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate videos by fusing 1-9 reference images with character-mapped prompts”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
This skill wraps Alibaba Cloud's HappyHorse 1.0 text-to-video model through the async DashScope video-synthesis API. Submit a text prompt and configure resolution (720P or 1080P), aspect ratio, duration (3–15 seconds), and optional seed for reproducibility; the skill polls for task completion and returns your generated MP4 video URL.
Aliyun Wan I2V taps DashScope's Wan 2.7 model to synthesize videos from static images asynchronously. It handles single-image generation, frame interpolation between two images, video extension from clips, and audio-driven animation with lip-sync capabilities.
This skill harnesses Alibaba's Wan 2.7 video editing model to transform video appearance through style transfer (clay, anime, etc.) or content-aware edits guided by text prompts and optional reference images. It handles async task creation, polling, and media validation across multiple aspect ratios and resolutions.
Aliyun Video Style Repaint applies one of eight preset artistic styles to your videos via Alibaba's DashScope API. Choose from Japanese manga, American comics, 3D cartoon, Chinese ink painting, paper art, and other effects, then submit your video for async processing and download the styled result.
This skill wraps Alibaba Cloud's DashScope Vidu video-synthesis API, enabling text-to-video, image-to-video, keyframe interpolation, and reference-subject generation. It handles async task creation, polling, and result retrieval across multiple Vidu model variants (Q3 Pro/Turbo, Q2) with configurable resolution, duration, audio, and watermark options.
This skill harnesses Alibaba Cloud's Wan R2V models to create multi-shot videos from reference video or image inputs while maintaining consistent character styling. It provides a normalized interface for async video generation with polling support and includes validation tooling to verify requests against the official model specifications.
More skills Happyhorse Video (NOASSERTION) · aliyun-wan-image (MIT) · Happyhorse (unlicensed)