Agent skill · creative production · aradotso
happy-horse-video-generator
happy-horse-video-generator — an agent skill for coding agents.
Why this skill is useful
Adds executable scripts for setting up and running the Happy Horse video generation model, which are not available in public documentation.
What it needs
Requires huggingface_hub, python installed locally. Requires huggingface account access. About 8k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
bash Clone the official repo once released git clone https://github.com/<official-org>/happy-horse-1.0 cd happy-horse-1.0 Create isolated environment python -m venv .venv source .venv/bin/activate # Windows: .venv\Scripts\activate Install dependencies (anticipated) pip install -r requirements.txt Download model weights (anticipated — likely via huggingfacehub) pip install huggingfacehub python -c " from huggingfacehub import snapshotdownload snapshotdownload( repoid='<official-org>/happy-horse-1.0', localdir='./weights/happy-horse-1.0' ) " bash Set before running inference export HFTOKEN=yourhuggingfacetoken # if weights are gated export HAPPYHORSEMODELPATH=./weights/happy-horse-1.0 export CUDAVISIBLEDEVICES=0 # target GPU index bash Anticipated multi-GPU launch torchrun --nprocpernode=4 generate.py \ --modelpath $HAPPYHORSEMODELPATH \ --prompt "A galloping horse across open plains at sunset" \ --resolution 1080p \ --steps 8 bash Text-to-video (distilled, 8 steps, no CFG) python generate.py \ --task t2v \ --modelpath $HAPPYHORSEMODELPATH \ --prompt "A horse galloping through a misty forest, hooves thundering on wet earth" \ --resolution 1080p \ --duration 5 \ --steps 8 \ --output ./output/horseforest.mp4 Image-to-video python generate.py \ --task i2v \ --modelpath $HAPPYHORSEMODELPATH \ --image ./reference.png \ --prompt "The horse rears up and gallops away into the distance" \ --resolution 1080p \ --duration 5 \ --steps 8 \ --output ./output/horsei2v.mp4 Base model (50 steps, CFG — higher quality, slower) python generate.py \ --task t2v \ --modelpath $HAPPYHORSEMODELPATH \ --variant base \ --prompt "..." \ --resolution 1080p \ --steps 50 \ --cfgscale 7.5 \ --output ./output/horsebase.mp4 python import os import torch from happyhorse import HappyHorsePipeline # module name TBC at release def generatevideofromtext( prompt: str, outputpath: str, resolution: str = "1080p", durationsec: int = 5, steps: int = 8, seed: int = 42, ) -> str: """ Generate a video (with native …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/happy-horse-video-generator