skills.rest
inference-sh
inference-shOFFICIAL
Explore all skills by this author →
WebsiteGitHub

happyhorse

Generate and edit videos with Alibaba HappyHorse 1.0 models via the inference.sh CLI.

723|101|Updated Jan 31, 2026
Search Tags:#video generation#video editing#text-to-video#image-to-video#inference.sh#alibaba#happyhorse
One-click install
npx skills add https://github.com/inference-sh/skills --skill happyhorse
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: happyhorse
Source: https://github.com/inference-sh/skills/tree/main/tools/video/happyhorse
Command: npx skills add https://github.com/inference-sh/skills --skill happyhorse

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating or editing video content normally requires filming, animation skills, or complex editing software. This Skill lets you generate physically realistic videos from text, images, or reference characters, and edit existing videos with natural language instructions, all through simple CLI commands.

Core Features & Use Cases

  • Text-to-Video and Image-to-Video: Generate 720P/1080P videos up to 15 seconds from prompts or animate a still image using HappyHorse T2V and I2V models.
  • Character Preservation (R2V): Keep characters consistent across generated videos using up to 9 reference images, ideal for recurring personas or product demos.
  • Natural Language Video Editing: Modify existing videos (backgrounds, weather, characters) with text instructions and optional audio control.
  • Use Case: A social media manager needs a 10-second clip of a brand mascot walking through a market. They supply one reference image to the R2V model and receive a character-consistent 1080P video without any filming.

Quick Start

Ask the agent to generate a 10-second 1080P video of a golden retriever running through autumn leaves using the HappyHorse text-to-video model.

Frequently Asked Questions about happyhorse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a video from text with HappyHorse?▼

Run belt app run alibaba/happyhorse-1-0-t2v with a JSON input containing your prompt, duration, resolution, and aspect ratio. The model returns a physically realistic video up to 15 seconds at 720P or 1080P.

How do I keep a character consistent across AI-generated videos?▼

Use the HappyHorse R2V model (alibaba/happyhorse-1-0-r2v) and pass up to 9 reference images in the reference_images parameter. The model preserves those characters in the generated scene described by your prompt.

Can HappyHorse edit existing videos with text instructions?▼

Yes, the happyhorse-1-0-video-edit model accepts an MP4/MOV video plus a natural language editing prompt. You can also supply up to 5 reference images and control audio with the audio_setting parameter (auto, generate, or keep_original).

What resolutions and durations does HappyHorse support?▼

All HappyHorse models support 720P and 1080P resolutions with durations from 3 to 15 seconds. Aspect ratios include 16:9, 9:16, 1:1, 4:3, 3:4, and 21:9 on T2V and R2V.

How much does HappyHorse video generation cost?▼

HappyHorse charges $0.14 per second at 720P and $0.24 per second at 1080P. Video Edit is billed on combined input and output duration.

Related Skills

Explore More Design & Creative Skills→
lostsock1lostsock1
1

filmmaker

Generate cinematic video clips and assemble them into final videos.

Community
Advanced
Marky-TeamMarky-Team
3

schedule-posts

Schedule and publish social media posts with captions and media via the Marky API.

Official
Advanced
ag47-ptag47-pt
1

motion-design

Plan motion design workflows from concepts to animated video experiences.

Community
Advanced
jorgeochipinti97jorgeochipinti97

ugc-video-prompting

Generate model-specific UGC video prompts for Veo 3 and Seedance 2.0 workflows.

Community
Advanced