Update README.md

README.md

@@ -9,4 +9,32 @@ tags:
 - Video Generative Model Training
 - Text-to-Video Diffusion Model Training
 - prompts
----
+---
+
+# Summary
+Here we provide pre-trained model weights on our OpenVid-1M in model_weights.
+
+**Project**: [https://nju-pcalab.github.io/projects/openvid](https://nju-pcalab.github.io/projects/openvid)
+
+**Paper**: [https://huggingface.co/papers/2407.02371](https://huggingface.co/papers/2407.02371)
+
+**Code**: [https://github.com/NJU-PCALab/OpenVid](https://github.com/NJU-PCALab/OpenVid)
+
+**Dataset**: [https://github.com/NJU-PCALab/OpenVid](https://huggingface.co/datasets/nkp37/OpenVid-1M)
+
+# Directory
+```
+model_weights
+   └─ MVDiT-16×512×512.pt
+   └─ STDiT-16×512×512.pt
+   └─ STDiT-16×1024×1024.pt
+```
+
+# Download
+You can download model weights by ```wget```, for instance:
+```
+wget https://huggingface.co/datasets/nkp37/OpenVid-1M/resolve/main/model_weights/MVDiT-16×512×512.pt
+wget https://huggingface.co/datasets/nkp37/OpenVid-1M/resolve/main/model_weights/STDiT-16×1024×1024.pt
+wget https://huggingface.co/datasets/nkp37/OpenVid-1M/resolve/main/model_weights/STDiT-16×512×512.pt
+```
+If you want to generate videos use our pre-trained model weights, please refer to [**here**](https://github.com/NJU-PCALab/OpenVid-1M#inference).