HappyHorse 1.0 オープンソースガイド：第1位のAIビデオモデルのインストール、実行、ファインチューン方法

import torch
from happyhorse import HappyHorseModel

# Load the model
model = HappyHorseModel.from_pretrained(
    "happy-horse/happyhorse-1.0",
    device="cuda",
    dtype=torch.float8_e4m3fn  # For FP8 quantization
)

# Generate video from text
prompt = "A woman in a blue dress holding our skincare product, smiling at the camera"
video, audio = model.generate(
    prompt=prompt,
    duration_seconds=5,
    fps=24,
    aspect_ratio="16:9",
    height=1080
)

# Save output
video.save("output.mp4")
audio.save("output.wav")

# Generate video with image conditioning
from PIL import Image
image = Image.open("product_image.jpg")
video_from_image, audio = model.generate(
    image=image,
    prompt="Show the product features, zoom in on the packaging",
    duration_seconds=8,
    fps=24
)

# Batch generation for multiple scripts
scripts = [
    "Woman in gym holding protein powder",
    "Man at home desk with laptop",
    "Group of friends laughing with phone"
]

for script in scripts:
    video, audio = model.generate(prompt=script, duration_seconds=5)
    video.save(f"video_{scripts.index(script)}.mp4")

# Dockerfile
FROM nvidia/cuda:12.1-runtime-ubuntu22.04

RUN apt-get update && apt-get install -y \
    python3.10 python3-pip git \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

COPY requirements.txt .
RUN pip install -r requirements.txt

COPY . .

EXPOSE 8000

CMD ["python3", "-m", "happyhorse.server", "--host", "0.0.0.0", "--port", "8000"]

# requirements.txt
torch==2.1.0
torchvision==0.16.0
happyhorse==1.0.0
fastapi==0.104.1
uvicorn==0.24.0
python-multipart==0.0.6
pillow==10.1.0