Welcome to FastVideo#
FastVideo is a unified inference and post-training framework for accelerated video generation.
FastVideo is an inference and post-training framework for diffusion models. It features an end-to-end unified pipeline for accelerating diffusion models, starting from data preprocessing to model training, finetuning, distillation, and inference. FastVideo is designed to be modular and extensible, allowing users to easily add new optimizations and techniques. Whether it is training-free optimizations or post-training optimizations, FastVideo has you covered.
Key Features#
FastVideo has the following features:
State-of-the-art performance optimizations for inference
E2E post-training support
Data preprocessing pipeline for video data.
Sparse distillation for Wan2.1 and Wan2.2 using Video Sparse Attention and Distribution Matching Distillation
Support full finetuning and LoRA finetuning for state-of-the-art open video DiTs.
Scalable training with FSDP2, sequence parallelism, and selective activation checkpointing, with near linear scaling to 64 GPUs.
Documentation#
Getting Started
Inference
Training
Distillation
Sliding Tile Attention
Video Sparse Attention
Design
Developer Guide
API Reference