Update README.md

README.md

@@ -31,7 +31,20 @@ Abstract: *This study seeks to automate camera movement control for filming exis
 Please refer to our [GitHub repo](https://github.com/hou-yz/dvgformer) for detailed installation steps.
 
 ## Usage
-Download the model first and put it under the `checkpoints/` directory.
+Assuming you have followed the Installation Steps from [GitHub repo](https://github.com/hou-yz/dvgformer), you can use the following code to load the model checkpoint
+```python
+import torch
+from src.models import DVGFormerModel
+
+model = DVGFormerModel.from_pretrained(
+    'yunzhong-hou/DVGFormer'
+    ).to('cuda').to(torch.bfloat16)
+```
+
+For blender evaluation, you can run the following script from the GitHub repo.
+```sh
+python blender_eval.py 
+```
 
 ## Citation
 If you find this project useful, please consider citing: