$npx skillfedfor your agent

Happyhorse

HappyHorse 1.0 is a video generation and editing skill powered by Alibaba's models, accessible via the inference.sh CLI. Create physically realistic videos from text prompts, animate still images, preserve characters across multiple reference photos, or edit existing footage with natural language instructions—all at 720P or 1080P up to 15 seconds.

HappyHorse generates and edits realistic videos using Alibaba's models through text, images, or natural language editing commands.

AI-generated summary based on this skill's SKILL.md

660 94 unlicensed, metadata onlyupdated by inference-sh

Decision gist · record as of 2026-07-26

HappyHorse generates and edits realistic videos using Alibaba's models through text, images, or natural language editing commands. HappyHorse 1.0 is a video generation and editing skill powered by Alibaba's models, accessible via the inference.sh CLI. Create physically realistic videos from text prompts, animate still images, preserve characters across multiple reference photos, or edit existing footage with natural language instructions—all at 720P or 1080P up to 15 seconds.

manual: git clone https://github.com/inference-sh/skills → cp -r skills ~/.claude/skills/happyhorse

Use it when

  • Happyhorse integrates with agents through the inference.sh CLI interface.
  • Happyhorse generates videos at 720P or 1080P resolution with a maximum duration of 15 seconds per clip.
Same gist for agents: .md · .json

Install

inference-sh/skills/happyhorse · repository language: Shell

generated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub

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

What is Happyhorse?

Happyhorse is a video generation and editing skill powered by Alibaba's models, accessible via the inference.sh CLI. It creates physically realistic videos from text prompts, animates still images, preserves characters across multiple reference photos, or edits existing footage with natural language instructions—all at 720P or 1080P up to 15 seconds.

How do I use Happyhorse with agents?

Happyhorse integrates with agents through the inference.sh CLI interface. You can configure it as a plugin or extension within your agent setup to enable video generation and editing capabilities. The skill accepts text prompts, image references, and editing instructions, making it straightforward to add video creation workflows to agent pipelines.

What video specifications does Happyhorse support?

Happyhorse generates videos at 720P or 1080P resolution with a maximum duration of 15 seconds per clip. The skill supports multiple generation modes including text-to-video creation, image animation, character preservation across reference photos, and natural language video editing.

What are Happyhorse's main features?

Happyhorse 1.0 offers text-to-video generation for creating realistic videos from prompts, image animation to bring still images to life, character consistency preservation across multiple reference photos, and natural language video editing for modifying existing footage. All outputs maintain physical realism powered by Alibaba's underlying models.

How do I access Happyhorse documentation and setup?

Happyhorse documentation and setup guides are available through the inference.sh CLI. The skill is designed for easy configuration as a plugin or extension. Refer to the inference.sh documentation for detailed setup instructions, configuration options, and integration examples for your specific use case.

What can I create with Happyhorse?

With Happyhorse, you can generate physically realistic videos from text descriptions, animate static images into dynamic video content, maintain consistent character appearances across multiple reference photos, and edit existing videos using natural language commands. All content is produced at professional resolutions up to 1080P.

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 › “Find and learn about the Happyhorse skill”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Seedance
by inference-sh · inference-sh/skills

Seedance creates videos from text, images, or reference material with built-in audio generation via ByteDance's Seedance 2.0 model. Choose from standard, fast, or studio variants supporting up to 1080p resolution and 4-15 second durations for social media, product demos, and animated content.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars
Image To Video
by inference-sh · inference-sh/skills

Transform still images into fluid video animations by selecting the right model for your content type—from realistic motion with Wan 2.5 i2v to specialized fabric physics with Fabric 1.0. Master motion prompting techniques, camera movement, and duration best practices to bring images to life with natural, subtle animation.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars
aliyun-vidu-video
by cinience · cinience/alicloud-skills

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.

MITupdated Jul 2026
★ 397repo stars
video-gen
by marswaveai · marswaveai/skills

Create AI-powered videos from text descriptions, images, or reference materials using three distinct model families. Choose HappyHorse for versatile text-to-video and editing, SeeDance for frame-based transitions, or PixVerse for specialized features like lip-sync, motion transfer, and marketing templates.

MITupdated Jul 2026
★ 75repo stars
aliyun-happyhorse-r2v
by cinience · cinience/alicloud-skills

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.

MITupdated Jul 2026
★ 397repo stars
Video Prompting Guide
by inference-sh · inference-sh/skills

Learn structured approaches to writing prompts that generate high-quality videos across leading AI models. This guide covers shot composition, camera techniques, lighting vocabulary, and style keywords, plus model-specific tips and real-world examples for product demos, documentaries, and more.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars

More skills Image Upscaling (unlicensed) · qwencloud-video-generation (Apache-2.0) · flow-media (MIT) · Happyhorse Video (NOASSERTION) · aliyun-happyhorse-t2v (MIT) · P Image (unlicensed)

Tags
inference-sh-toolequine-themedagent-extensionskill-integrationthird-party-plugin