skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

happyhorse

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

Updated Jul 28, 2026
Search Tags:#video generation#video editing#text-to-video#image-to-video#inference.sh#ai video#alibaba happyhorse
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill happyhorse-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: happyhorse
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/happyhorse
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill happyhorse-aadi-110i

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 photos, and edit existing videos with natural language instructions, all through simple CLI commands. ## Core Features & Use Cases - Text-to-Video (T2V): Generate videos from text prompts at 720P or 1080P, up to 15 seconds, in multiple aspect ratios. - Image-to-Video and Reference-to-Video (I2V/R2V): Animate a still image or preserve characters from up to 9 reference images for consistent multi-character scenes. - Natural Language Video Editing: Modify existing videos (backgrounds, characters, weather, audio) using plain text instructions with optional reference images. - Use Case: A marketing team needs a 10-second product demo clip with a consistent brand character. They provide a character reference photo and a scene prompt to the R2V model, then refine the result with the Video Edit model. ## Quick Start Ask the AI 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, plus optional duration (3-15 seconds), resolution (720P or 1080P), and aspect ratio. You must first install the inference.sh belt CLI and log in.

How to keep characters consistent across AI-generated videos?▼

Use the HappyHorse R2V model (alibaba/happyhorse-1-0-r2v) with the reference_images parameter, which accepts up to 9 character reference photos. The model preserves those characters in the generated scene, including multi-character compositions.

Can I edit an existing video with natural language instructions?▼

Yes, the HappyHorse Video Edit model accepts an MP4 or MOV video plus a text prompt describing the change, such as replacing a background or swapping a character using reference images. An audio_setting parameter controls whether audio is kept, generated, or auto-handled.

What resolutions and durations does HappyHorse support?▼

All HappyHorse models support 720P and 1080P output with durations from 3 to 15 seconds. Pricing is $0.14 per second at 720P and $0.24 per second at 1080P, with Video Edit billed on input plus output duration.

What are the limitations of reference-to-video generation?▼

R2V accepts a maximum of 9 reference images, and Video Edit accepts up to 5. Videos are capped at 15 seconds, and input videos for editing must be MP4 or MOV with H.264 encoding.

Related Skills

Explore More Design & Creative Skills→
Qo-qiaoQo-qiao
38

Portrait Photography

Generates professional portrait photography prompts with lighting design, lens language, and realism techniques for Z-Image and Krea 2.

Community
Intermediate
apexradiusapexradius

video-produce

Automate video production with Gemini API and ffmpeg.

Official
Advanced
ChatCut-IncChatCut-Inc
751

video-gen

Generate AI video clips from text, images, and reference footage.

Official
Advanced
jorgeochipinti97jorgeochipinti97

ugc-video-prompting

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

Community
Advanced