Update README.md

README.md

@@ -6,17 +6,45 @@ pipeline_tag: text-to-image
 ---
 # ImageReward
 
-ImageReward is the first general-purpose text-to-image human preference RM which is trained on in total 137k pairs of expert comparisons, based on text prompts and corresponding model outputs from DiffusionDB. We demonstrate that ImageReward outperforms existing text-image scoring methods, such as CLIP, Aesthetic, and BLIP, in terms of understanding human preference in text-to-image synthesis through extensive analysis and experiments.
+<p align="center">
+   🤗 <a href="https://huggingface.co/THUDM/ImageReward" target="_blank">HF Repo</a> • 🐦 <a href="https://twitter.com/thukeg" target="_blank">Twitter</a> • 📃 <a href="https://arxiv.org/abs/2304.05977" target="_blank">Paper</a> <br>
+</p>
 
-## Approach
+**ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation**
 
-![ImageReward](ImageReward.png)
+ImageReward is the first general-purpose text-to-image human preference RM which is trained on in total 137k pairs of
+expert comparisons, based on text prompts and corresponding model outputs from DiffusionDB. We demonstrate that
+ImageReward outperforms existing text-image scoring methods, such as CLIP, Aesthetic, and BLIP, in terms of
+understanding human preference in text-to-image synthesis through extensive analysis and experiments.
 
-## Setup
+<p align="center">
+    <img src="figures/ImageReward.png" width="700px">
+</p>
 
-* Environment: install dependencies via `pip install -r requirements.txt`. 
+## Quick Start
 
-## Usage
+### Install Dependency
+
+We have integrated the whole repository to a single python package `image-reward`. Following the commands below to prepare the environment:
+
+```shell
+# Clone the ImageReward repository (containing data for testing)
+git clone https://github.com/THUDM/ImageReward.git
+cd ImageReward
+
+# Install the integrated package `image-reward`
+pip install image-reward
+```
+
+### Example Use
+
+We provide example images in the [`assets/images`](assets/images) directory of this repo. The example prompt is:
+
+```text
+a painting of an ocean with clouds and birds, day time, low depth field effect
+```
+
+Use the following code to get the human preference scores from ImageReward:
 
 ```python
 import os
@@ -28,7 +56,7 @@ if __name__ == "__main__":
     img_prefix = "assets/images"
     generations = [f"{pic_id}.webp" for pic_id in range(1, 5)]
     img_list = [os.path.join(img_prefix, img) for img in generations]
-    model = reward.load()
+    model = reward.load("ImageReward-v1.0")
     with torch.no_grad():
         ranking, rewards = model.inference_rank(prompt, img_list)
         # Print the result
@@ -41,7 +69,7 @@ if __name__ == "__main__":
 
 ```
 
-The output will look like the following (the exact numbers may be slightly different depending on the compute device):
+The output should be like as follow (the exact numbers may be slightly different depending on the compute device):
 
 ```
 Preference predictions: