tokix / fifo-diffusion_public Goto Github PK

git clone [email protected]:jjihwan/FIFO-Diffusion_public.git
cd FIFO-Diffusion_public

python3 -m venv .fifo
source .fifo/bin/activate

pip install -r requirements.txt

cd FIFO-Diffusion_public
    .
    └── videocrafter_models
        └── base_512_v2
            └── model.ckpt      # VideoCrafter2 checkpoint

python3 videocrafter_main.py --save_frames

python3 videocrafter_main_mp.py --num_gpus 8 --save_frames

cd FIFO-Diffusion_public
git clone [email protected]:PKU-YuanGroup/Open-Sora-Plan.git

python -m venv .sora
source .sora/bin/activate

cd Open-Sora-Plan
pip install -e .

sh scripts/opensora_fifo_ddpm.sh

python3 -m venv .fifo
source .fifo/bin/activate

pip install -r requirements.txt

mkdir zeroscope_models         # directory where the model will be stored
python3 zeroscope_main.py

@article{kim2024fifo,
	title = {FIFO-Diffusion: Generating Infinite Videos from Text without Training},
	author = {Jihwan Kim and Junoh Kang and Jinyoung Choi and Bohyung Han},
	journal = {arXiv preprint arXiv:2405.11473},
	year = {2024},
}