42 lines
2.6 KiB
Markdown
42 lines
2.6 KiB
Markdown
# Welcome to FastVideo
|
|
|
|
FastVideo is an inference and post-training framework for video diffusion models. One pipeline covers data preprocessing, fine-tuning, distillation, and inference. Attention backends, parallelism, and quantization are separate modules, so you can add one without changing model code.
|
|
|
|
## Key Features
|
|
|
|
FastVideo has the following features:
|
|
|
|
- End-to-end post-training support for bidirectional and autoregressive models
|
|
- Full finetuning and LoRA [finetuning](training/finetune.md) for state-of-the-art open video DiTs
|
|
- [Data preprocessing pipeline](training/data_preprocess.md) for video, image, and text data
|
|
- [Distribution Matching Distillation (DMD2)](distillation/dmd.md) stepwise distillation
|
|
- Sparse attention with [Video Sparse Attention](attention/vsa/index.md)
|
|
- [Sparse distillation](https://hao-ai-lab.github.io/blogs/fastvideo_post_training/) to achieve >50x denoising speedup
|
|
- [Attn-QAT training](training/attn_qat.md) for quantization-aware post-training
|
|
- Causal distillation through Self-Forcing
|
|
- Scalable training with FSDP2, sequence parallelism, and selective activation checkpointing
|
|
- See the [training overview](training/overview.md) for the full training workflow
|
|
- State-of-the-art performance optimizations for inference
|
|
- Sequence parallelism for distributed inference
|
|
- Multiple state-of-the-art [attention backends](attention/index.md)
|
|
- User-friendly [CLI](inference/cli.md) and Python API
|
|
- See the [support matrix](inference/support_matrix.md) for supported models and [optimizations](inference/optimizations.md) for the full list
|
|
- Realtime video generation and editing
|
|
- [Dreamverse](https://github.com/hao-ai-lab/FastVideo/tree/main/apps/dreamverse): stream and "vibe direct" video in realtime ([live demo](https://dreamverse.fastvideo.org/))
|
|
|
|
## Documentation
|
|
|
|
Welcome to FastVideo! This documentation will help you get started with our unified inference and post-training framework for accelerated video generation.
|
|
|
|
Use the navigation menu on the left to explore different sections:
|
|
|
|
- **Getting Started**: Installation and quick start guides
|
|
- **Inference**: Learn how to use FastVideo for video generation
|
|
- **Training**: Data preprocessing and fine-tuning workflows
|
|
- **Distillation**: Post-training optimization techniques
|
|
- **Sliding Tile Attention**: Legacy workflow docs and kernel notes
|
|
- **Video Sparse Attention**: Efficient attention for video models
|
|
- **Design**: Framework architecture and design principles
|
|
- **Developer Guide**: Contributing and development setup
|
|
- **API Reference**: Complete API documentation
|