update readme

README.md

@@ -3,14 +3,13 @@ license: apache-2.0
 language:
 - en
 tags:
-- diffusion model
-- DiT
-- ACE
+- Diffusion Transformer
+- Image Editing
 - Scepter
-- Scepter studio
+- ACE
 ---
 <h2 align="center">
-    <img src="assets/figures/icon.png" height=17> : All-round Creator and Editor Following Instructions via Diffusion Transformer
+    ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer
 </h2>
 
 <h3 align="center">
@@ -19,11 +18,15 @@ tags:
 
 <div align="center">
 
-[**Paper (ArXiv)**](https://arxiv.org/abs/2410.00086) **|** [**Project Page**](https://ali-vilab.github.io/ace-page/) **|** [**Code**](https://github.com/modelscope/scepter)
+[**Paper**](https://arxiv.org/abs/2410.00086) **|** [**Project Page**](https://ali-vilab.github.io/ace-page/) **|** [**Code**](https://github.com/modelscope/scepter)
 
 </div>
 
 
+ACE is a unified foundational model framework that supports a wide range of visual generation tasks. 
+By defining CU for unifying multi-modal inputs across different tasks and incorporating long-context CU, 
+we introduce historical contextual information into visual generation tasks, paving
+the way for ChatGPT-like dialog systems in visual generation.
 
 <p>
   <table align="center">
@@ -36,10 +39,6 @@ tags:
 </p>
 
 
-ACE is a unified foundational model framework that supports a wide range of visual generation tasks. By defining CU for unifying multi-modal inputs across different tasks and incorporating long-
-context CU, we introduce historical contextual information into visual generation tasks, paving
-the way for ChatGPT-like dialog systems in visual generation.
-
 
 ## BibTeX