hao-ai-lab-FastVideo/docs/getting_started/quick_start.md

Quick start

Install FastVideo, generate one video, then start from a maintained recipe.

Install

Requires Python 3.10 to 3.12 and CUDA 12.6 or newer.

uv venv --python 3.12 --seed
source .venv/bin/activate

# CUDA 12. Use cu130 on CUDA 13.
UV_TORCH_BACKEND=cu126 uv pip install fastvideo

For the fastest attention kernels, install flash-attn:

uv pip install flash-attn --no-build-isolation -v

Generate a video

from fastvideo import VideoGenerator

generator = VideoGenerator.from_pretrained(
    "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
    num_gpus=1,
    text_encoder_cpu_offload=True,
)
generator.generate_video(
    "A raccoon peers through a field of sunflowers.",
    output_path="videos/",
    save_video=True,
)

The first run downloads the Wan2.1 1.3B checkpoint. The call writes an MP4 under videos/. The full example is examples/inference/basic/basic.py.

Choose a maintained recipe

The cookbook selects complete, checked-in recipes instead of mixing model, parallelism, offload, and attention settings independently.

Open the inference cookbook

:::tip[Need more control?] Start from a maintained recipe, then use the configuration and optimization guides for supported changes. :::

Next Steps

• Inference Cookbook - Choose a maintained recipe
• Installation Guide - Detailed installation instructions
• Configuration - Learn about configuration options
• Examples - Explore more examples
• Optimizations - Performance optimization tips