Update README.md

README.md

@@ -11,7 +11,7 @@ tags:
 - unified-model
 ---
 
-# 🌌 Skywork/UniPic2-SD3.5M-Kontext-2B
+# UniPic2-SD3.5M-Kontext-2B
 
 <div align="center">   
   <img src="skywork-logo.png" alt="Skywork Logo" width="500"> 
@@ -27,37 +27,22 @@ tags:
 
 ## 📖 Introduction
 
-**Skywork-UniPic** is a **unified autoregressive multimodal model** with **1.5 billion parameters**, capable of handling three key vision-language tasks within a single architecture:
+**UniPic2-SD3.5M-Kontext-2B** is a 2B-parameter post-trained model built on the SD3.5-Medium family. It focuses on text-to-image generation and image editing, delivering strong quality with a fast generation speed. It runs smoothly on a single 16 GB consumer GPU.
 
-- 🖼️ **Image Understanding**  
-- 🎨 **Text-to-Image Generation**  
-- ✏️ **Image Editing**
-
-Trained from scratch on a large-scale multimodal corpus, UniPic is designed to support a wide range of unified image-text tasks efficiently.
-
-<div align="center">   
-  <img src="teaser.png" alt="Model Teaser" width="700">  
-</div>
-
-
----
+<div align="center"> <img src="teaser.png" alt="Model Teaser" width="720"> </div>
 
 ## 📊 Benchmarks
 
-Skywork-UniPic achieves competitive results across a variety of vision-language tasks:
+UniPic2-SD3.5M-Kontext-2B w/o GRPO achieves competitive results across a variety of vision-language tasks:
 
 | Task               | Score  |
 |--------------------|--------|
-| 🧠 **GenEval**       | 0.86   |
-| 🖼️ **DPG-Bench**     | 85.5   |
-| ✂️ **GEditBench-EN** | 5.83   |
-| 🧪 **ImgEdit-Bench** | 3.49   |
+| 🧠 **GenEval**       | 0.83   |
+| 🖼️ **DPG-Bench**     | 83.7   |
+| ✂️ **GEditBench-EN** | 6.31   |
+| 🧪 **ImgEdit-Bench** | 3.95   |
 
-<div align="center">   
-  <img src="UniPic.png" alt="Benchmark Results" width="700">  
-</div>
 
----
 
 ## 🧠 Usage