Update README.md

README.md

@@ -6,7 +6,30 @@ license: cc-by-nc-4.0
 - base model [zeroscope_v2_576w](https://huggingface.co/cerspense/zeroscope_v2_576w).
 - Train on [potat1](https://huggingface.co/camenduru/potat1#dataset--config) [dataset](https://huggingface.co/camenduru/potat1_dataset)  with 50000 steps for 10 hours on single GPU of 24GB VRAM.
 
----
-widget:
-- text: "0"
----
+# Install Windows
+```batch
+git clone https://github.com/ExponentialML/Text-To-Video-Finetuning.git
+cd Text-To-Video-Finetuning
+git lfs install
+git clone https://huggingface.co/damo-vilab/text-to-video-ms-1.7b ./models/model_scope_diffusers/
+py -m venv --clear venv && venv\Scripts\activate
+pip install -r requirements.txt
+pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 --no-cache --force-reinstall --version --isolated --ignore-installed
+
+git clone https://github.com/ExponentialML/Video-BLIP2-Preprocessor.git
+cd Video-BLIP2-Preprocessor
+pip install -r requirements.txt
+
+:: fix1
+echo accelerate^>=0.20.3>>requirements-dev.txt
+pip install -r requirements-dev.txt
+
+:: Captation
+python preprocess.py --video_directory C:\Video-BLIP2-Preprocessor\videos --config_name "My Videos" --config_save_name "my_videos"
+
+:: Training
+venv\Scripts\activate && python train.py --config ./configs/v2/train_config.yaml
+
+:: inference  1024x576
+python 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
+```