Update README.md

README.md

@@ -14,55 +14,38 @@ European Conference on Computer Vision (ECCV), 2024
 
 - [25.07.2024] Release weights and inference code for VFusion3D.
 
-## Results and Comparisons
-
-### 3D Generation Results
-<img src='https://github.com/facebookresearch/vfusion3d/blob/main/images/user.png' width=950>
 
-<img src='https://github.com/facebookresearch/vfusion3d/blob/main/images/gif2.gif' width=950>
 
-### User Study Results
-<img src='https://github.com/facebookresearch/vfusion3d/blob/main/images/user.png' width=950>
+## Quick Start
 
+Getting started with VFusion3D is super easy! 🤗 Here’s how you can use the model with Hugging Face:
 
-## Setup
+### Use a pipeline as a high-level helper
+```python
+from transformers import pipeline
 
-### Installation
-```
-git clone https://github.com/facebookresearch/vfusion3d
-cd vfusion3d
+pipe = pipeline("feature-extraction", model="jadechoghari/vfusion3d", trust_remote_code=True)
 ```
 
-### Environment
-We provide a simple installation script that, by default, sets up a conda environment with Python 3.8.19, PyTorch 2.3, and CUDA 12.1. Similar package versions should also work.
+### Load model directly
+```python
+from transformers import AutoModel
 
+model = AutoModel.from_pretrained("jadechoghari/vfusion3d", trust_remote_code=True)
 ```
-source install.sh
-```
-
-## Quick Start
 
-### Pretrained Models
+Check out our [demo app](#) to see VFusion3D in action! 🤗
 
-- Model weights are available here [Google Drive](https://drive.google.com/file/d/1b-KKSh9VquJdzmXzZBE4nKbXnbeua42X/view?usp=sharing). Please download it and put it inside ./checkpoints/
+## Results and Comparisons
 
+### 3D Generation Results
+<img src='assets/gif1.gif' width=950>
 
-### Prepare Images
-- We put some sample inputs under `assets/40_prompt_images`, which is the 40 MVDream prompt images used in the paper. Results of them are also provided under `results/40_prompt_images_provided`. 
+<img src='assets/gif2.gif' width=950>
 
-### Inference
-- Run the inference script to get 3D assets.
-- You may specify which form of output to generate by setting the flags `--export_video` and `--export_mesh`.
-- Change `--source_path` and `--dump_path` if you want to run it on other image folders. 
+### User Study Results
+<img src='assets/user.png' width=950>
 
-    ```
-    # Example usages
-    # Render a video
-    python -m lrm.inferrer --export_video --resume ./checkpoints/vfusion3dckpt
-    
-    # Export mesh
-    python -m lrm.inferrer --export_mesh --resume ./checkpoints/vfusion3dckpt
-    ```
 
 
 ## Acknowledgement