Add badges

README.md

@@ -9,6 +9,14 @@ tags:
   <img src="asset/logo.png"  height=120>
 </p>
 
+<div style="display:flex;">
+  <a href="https://huggingface.co/spaces/PixArt-alpha/PixArt-alpha"><img src="https://img.shields.io/static/v1?label=Demo&message=Huggingface%20Gradio&color=orange"></a> &ensp;
+  <a href="https://pixart-alpha.github.io/"><img src="https://img.shields.io/static/v1?label=Project&message=Github&color=blue"></a> &ensp;
+  <a href="https://arxiv.org/abs/2310.00426"><img src="https://img.shields.io/badge/arXiv-2310.00426-b31b1b.svg?style=flat-square"></a> &ensp;
+  <a href="[default.asp](https://huggingface.co/spaces/PixArt-alpha/PixArt-alpha)"><img src="https://img.shields.io/static/v1?label=Demo&message=Huggingface%20Gradio&color=orange"></a> &ensp;
+
+</div>
+
 # 🐱 Pixart-α Model Card
 ![row01](asset/images/teaser.png)
 
@@ -65,14 +73,14 @@ The Pixart-α base model performs comparable or even better than the existing st
 
 ### 🧨 Diffusers 
 
-Make sure to upgrade diffusers to >= 0.19.0:
+Make sure to upgrade diffusers to >= 0.22.0:
 ```
-pip install diffusers --upgrade
+pip install -U diffusers --upgrade
 ```
 
-In addition make sure to install `transformers`, `safetensors`, `accelerate` as well as the invisible watermark:
+In addition make sure to install `transformers`, `safetensors`, and `accelerate`:
 ```
-pip install invisible_watermark transformers accelerate safetensors
+pip install transformers accelerate safetensors
 ```
 
 To just use the base model, you can run:
@@ -131,6 +139,7 @@ The model was not trained to be factual or true representations of people or eve
 
 ### Limitations
 
+
 - The model does not achieve perfect photorealism
 - The model cannot render legible text
 - The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”