Update README.md

README.md

@@ -21,7 +21,7 @@ FaceXFormer is an end-to-end unified model capable of handling a comprehensive r
 landmark detection, head pose estimation, attributes recognition, age/gender/race estimation and landmarks visibility prediction.
 
 <div  align="center">
-<!-- <img src='assets/samples_short.jpg'> -->
+<img src='assets/intro_viz.png'>
 </div>
 
 ## Model Details
@@ -29,6 +29,9 @@ landmark detection, head pose estimation, attributes recognition, age/gender/rac
 FaceXFormer is a transformer-based encoder-decoder architecture where each task is treated as a learnable token, enabling the 
 integration of multiple tasks within a single framework.
 
+<div  align="center">
+<img src='assets/main_archi.png'>
+</div>
 
 ## Usage
 
@@ -36,7 +39,7 @@ The models can be downloaded directly from this repository or using python:
 ```python
 from huggingface_hub import hf_hub_download
 
-hf_hub_download(repo_id="kartiknarayan/facexformer", filename="facexformer/ckpts/model.pt", local_dir="./models")
+hf_hub_download(repo_id="kartiknarayan/facexformer", filename="facexformer/ckpts/model.pt", local_dir="./ckpts")
 ```
 
 Please check our [GitHub repository](https://github.com/Kartik-3004/facexformer) for complete inference instructions.