happyhorse

What is happyhorse

Happy Horse 1.0 is an open-source AI video generation model developed by the Happy Horse team. It is a 15-billion-parameter unified Transformer that jointly generates video and synchronized audio from text or image prompts, offering cinematic 1080p quality and multilingual lip-sync.

How to use happyhorse

1. Clone the repository: git clone https://github.com/happy-horse/happyhorse-1.git
2. Navigate to the directory: cd happyhorse-1
3. Install dependencies: pip install -r requirements.txt
4. Download model weights: bash download_weights.sh
5. Generate video from the command line: python demo_generate.py --prompt "a robot dancing on the moon" --duration 5 Alternatively, use the Python API:

from happyhorse import HappyHorseModel
 
model = HappyHorseModel.from_pretrained("happy-horse/happyhorse-1.0")
 
video, audio = model.generate(
    prompt="an elder on a mountain peak overlooking the valley",
    duration_seconds=5,
    fps=24,
    language="en",
)
 
video.save("output.mp4")
audio.save("output.wav")

Features of happyhorse

• Unified Transformer: A 40-layer self-attention network for single-stream processing.
• Joint Video + Audio Generation: Produces synchronized dialogue, ambient sound, and Foley alongside video.
• 8-Step DMD-2 Distillation: Accelerated denoising process.
• Multilingual Lip-Sync: Supports English, Mandarin, Cantonese, Japanese, Korean, German, and French.
• 1080p Output: Generates 5–8 second clips at 1080p resolution.
• Open Source & Self-Hostable: Includes base model, distilled model, super-resolution module, and inference code with commercial-use permission.

Use Cases of happyhorse

• Social media content creation
• Advertising
• Cinematic applications

FAQ

What is Happy Horse 1.0? Happy Horse 1.0 is a 15B-parameter open-source AI video generation model that jointly produces video and synchronized audio from text or image prompts.

Is Happy Horse free for commercial use? Yes. Happy Horse is released as open source with commercial-use rights, including the base model, distilled model, super-resolution module, and inference code.

What hardware do I need to run Happy Horse? An NVIDIA H100 or A100 GPU with at least 48GB VRAM is recommended. A 5-second 1080p clip generates in roughly 38 seconds on H100.

Which languages does Happy Horse support for lip-sync? Seven languages: English, Mandarin, Cantonese, Japanese, Korean, German, and French — with industry-leading low Word Error Rate.

How does Happy Horse compare to OVI and LTX? Happy Horse 1.0 outperforms OVI 1.1 (80.0% win rate) and LTX 2.3 (60.9% win rate) across visual quality, prompt alignment, and Word Error Rate.