StreamDiffusionV2: An Open-Source Streaming System for Real-Time Interactive Video Generation

Tianrui Feng^*,1, Zhi Li¹, Haocheng Xi¹, Muyang Li², Shuo Yang¹, Xiuyu Li¹, Lvmin Zhang³, Kelly Peng⁴, Song Han², Maneesh Agrawala³, Kurt Keutzer¹, Akio Kodaira¹, Chenfeng Xu^†,1,5

¹UC Berkeley ²MIT ³Stanford University ⁴First Intelligence ⁵UT Austin

^† Project lead, corresponding to xuchenfeng@berkeley.edu

^* Work done when Tianrui Feng was a visiting student at UC Berkeley advised by Chenfeng Xu.

Overview

StreamDiffusionV2 is an open-source interactive diffusion pipeline for real-time streaming applications. It scales across diverse GPU setups, supports flexible denoising steps, and delivers high FPS for creators and platforms. Further details are available on our project homepage.

News

[2025-10-18] Release our model checkpoint on huggingface
[2025-10-06] 🔥 Our StreamDiffusionV2 is publicly released! Check our project homepage for more details.

Prerequisites

OS: Linux with NVIDIA GPU
CUDA-compatible GPU and drivers

Installation

conda create -n stream python=3.10.0
conda activate stream
# Require CUDA 12.4 or above, please check via `nvcc -V`
pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu124
pip install -r requirements.txt 
python setup.py develop

Download Checkpoints

huggingface-cli download --resume-download Wan-AI/Wan2.1-T2V-1.3B --local-dir wan_models/Wan2.1-T2V-1.3B
huggingface-cli download --resume-download jerryfeng/StreamDiffusionV2 --local-dir ./ckpts/wan_causal_dmd_v2v

Offline Inference

Single GPU

python streamv2v/inference.py \
--config_path configs/wan_causal_dmd_v2v.yaml \
--checkpoint_folder ckpts/wan_causal_dmd_v2v \
--output_folder outputs/ \
--prompt_file_path prompt.txt \
--video_path original.mp4 \
--height 480 \
--width 832 \
--fps 16 \
--step 2

Note: --step sets how many denoising steps are used during inference.

Multi-GPU

torchrun --nproc_per_node=2 --master_port=29501 streamv2v/inference_pipe.py \
--config_path configs/wan_causal_dmd_v2v.yaml \
--checkpoint_folder ckpts/wan_causal_dmd_v2v \
--output_folder outputs/ \
--prompt_file_path prompt.txt \
--video_path original.mp4 \
--height 480 \
--width 832 \
--fps 16 \
--step 2
# --schedule_block  # optional: enable block scheduling

Note: --step sets how many denoising steps are used during inference. Enabling --schedule_block can provide optimal throughput.

Adjust --nproc_per_node to your GPU count. For different resolutions or FPS, change --height, --width, and --fps accordingly.

Online Inference (Web UI)

A minimal web demo is available under demo/. For setup and startup, please refer to demo.

Access in a browser after startup: http://0.0.0.0:7860 or http://localhost:7860

To-do List

Acknowledgements

StreamDiffusionV2 is inspired by the prior works StreamDiffusion and StreamV2V. Our Causal DiT builds upon CausVid, and the rolling KV cache design is inspired by Self-Forcing.

We are grateful to the team members of StreamDiffusion for their support. We also thank First Intelligence and Daydream team for their great feedback.

We also especially thank DayDream team for the great collaboration and incorporating our StreamDiffusionV2 pipeline into their cool Demo UI.

Citation

If you find this repository useful in your research, please consider giving a star ⭐ or a citation.

@article{streamdiffusionv2,
  title={StreamDiffusionV2: An Open-Sourced Interactive Diffusion Pipeline for Streaming Applications},
  author={Tianrui Feng and Zhi Li and Haocheng Xi and Muyang Li and Shuo Yang and Xiuyu Li and Lvmin Zhang and Kelly Peng and Song Han and Maneesh Agrawala and Kurt Keutzer and Akio Kodaira and Chenfeng Xu},
  journal={Project Page},
  year={2025},
  url={https://streamdiffusionv2.github.io/}
}

chenfengxu714/StreamDiffusionV2