DiffuseSlide: Training-Free High Frame Rate Video Generation Diffusion
Geunmin Hwang, Hyun-kyu Ko, Younghyun Kim, Seungryong Lee, Eunbyung Park
DiffuseSlide is a training-free framework for generating high frame-rate videos.
It leverages noise re-injection and sliding-window latent denoising to enhance temporal consistency and visual quality without additional fine-tuning.
- Python 3.10.15
- CUDA 11.8 or CUDA 12.1
torch==2.1.1diffusers==0.27.2
conda create -n DiffuseSlide python=3.10.15 -y
conda activate DiffuseSlidepip install torch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 torchmetrics xformers --index-url https://download.pytorch.org/whl/cu118
pip install -r requirements.txtpip install torch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 torchmetrics xformers --index-url https://download.pytorch.org/whl/cu121
pip install -r requirements.txtCUDA_VISIBLE_DEVICES=0 python inference.py --config configs/4x_config.yamlCUDA_VISIBLE_DEVICES=0 python inference.py --config configs/2x_config.yamlIf you find our work useful, please consider citing:
@misc{hwang2025diffuseslide,
title={DiffuseSlide: Training-Free High Frame Rate Video Generation Diffusion},
author={Geunmin Hwang and Hyun-kyu Ko and Younghyun Kim and Seungryong Lee and Eunbyung Park},
year={2025},
eprint={2506.01454},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2506.01454}
}