Views
No views yet
1git clone https://github.com/ExponentialML/Text-To-Video-Finetuning.git
2cd Text-To-Video-Finetuning
3git lfs install
4git clone https://huggingface.co/damo-vilab/text-to-video-ms-1.7b ./models/model_scope_diffusers/
5py -m venv --clear venv && venv\Scripts\activate
6pip install -r requirements.txt
7pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 --no-cache --force-reinstall --version --isolated --ignore-installed
8
9git clone https://github.com/ExponentialML/Video-BLIP2-Preprocessor.git
10cd Video-BLIP2-Preprocessor
11pip install -r requirements.txt
12
13:: fix1
14echo accelerate^>=0.20.3>>requirements-dev.txt
15pip install -r requirements-dev.txt
16
17:: Captation
18python preprocess.py --video_directory C:\Video-BLIP2-Preprocessor\videos --config_name "My Videos" --config_save_name "my_videos"
19
20:: Training
21venv\Scripts\activate && python train.py --config ./configs/v2/train_config.yaml
22
23:: inference 1024x576
24python inference.py --model zeroscope_v2_576w_potat1\zeroscope_v2_576w-checkpoint-50000 --prompt "a fast moving fancy sports car" --fps 24 --num-frames 30 --window-size 12 --width 1024 --height 576 --sdp