flashvideo 0.1.0

flashvideo is a lightweight framework for accelerating large video diffusion models.

FastVideo is an open-source framework for accelerating large video diffusion model.

Get 8X diffusion boost for Mochi with FastVideo

🤗 FastMochi | 🤗 FastHunyuan

FastVideo currently offers: (with more to come)

• FastHunyuan and FastMochi: consistency distilled video diffusion models for 8x inference speedup.
• First open video DiT distillation recipes based on PCM.
• Scalable training with FSDP, sequence parallelism, and selective activation checkpointing, with near linear scaling to 64 GPUs.
• Memory efficient finetuning with LoRA, precomputed latents, and precomputed text embeddings.

Change Log

• 2024/12/17: FastVideo v0.1 is released.

🔧 Installation

The code is tested on Python 3.10.0, CUDA 12.1 and H100.

./env_setup.sh fastvideo

🚀 Inference

We recommend using a GPU with 80GB of memory. To run the inference, use the following command:

FastHunyuan

# Download the model weight
python scripts/huggingface/download_hf.py --repo_id=FastVideo/FastHunyuan --local_dir=data/FastHunyuan --repo_type=model
# CLI inference
sh scripts/inference/inference_hunyuan.sh

You can also inference FastHunyuan in the official Hunyuan github.

FastMochi

# Download the model weight
python scripts/huggingface/download_hf.py --repo_id=FastVideo/FastMochi-diffusers --local_dir=data/FastMochi-diffusers --repo_type=model
# CLI inference
bash scripts/inference/inference_mochi_sp.sh

Distillation

Please refer to the distillation guide.

Finetuning

Please refer to the finetuning guide.

Development Plan

Acknowledgement

We learned and reused code from the following projects: PCM, diffusers, and OpenSoraPlan.