Update README.md

README.md

@@ -3,19 +3,20 @@ license: cc-by-nc-nd-4.0
 ---
 
 # RealCustom Series
-<p align="center">
-<img src="assets/teaser.svg" width=95% height=95% 
-class="center">
-</p>
+
+<div style="display:flex;justify-content: center">
+<a href="https://corleone-huang.github.io/RealCustom_plus_plus/"><img alt="Build" src="https://img.shields.io/badge/Project%20Page-RealCustom-yellow"></a> 
+<a href="https://arxiv.org/pdf/2408.09744"><img alt="Build" src="https://img.shields.io/badge/arXiv%20paper-2504.02160-b31b1b.svg"></a>
+<a href="https://github.com/bytedance/RealCustom"><img src="https://img.shields.io/static/v1?label=GitHub&message=Code&color=green&logo=github"></a>
+</div>
+
+![teaser of RealCustom](./assets/teaser.svg)
 
 ## 📖 Introduction
 
 Existing text-to-image customization methods (i.e., subject-driven generation) face a fundamental challenge due to the entangled influence of visual and textual conditions. This inherent conflict forces a trade-off between subject fidelity and textual controllability, preventing simultaneous optimization of both objectives.We present RealCustom to disentangle subject similarity from text controllability and thereby allows both to be optimized simultaneously without conflicts. The core idea of RealCustom is to represent given subjects as real words that can be seamlessly integrated with given texts, and further leveraging the relevance between real words and image regions to disentangle visual condition from text condition.
 
-<p align="center">
-<img src="assets/process.svg" width=95% height=95% 
-class="center">
-</p>
+![process of RealCustom](./assets/process.svg)
 
 ## ⚡️ Quick Start
 
@@ -36,26 +37,6 @@ bash inference/inference_single_image.sh
 python inference/app.py
 ```
 
-### 🎨 Enjoy on [Dreamina](https://jimeng.jianying.com/ai-tool/home)
-RealCustom is previously commercially applied in Dreamina and Doubao, ByteDance. You can also enjoy the more advanced customization algorithm in Dreamina!
-
-#### Step 1: Create A Character: 
-Create character images and corresponding appearance descriptions through prompt descriptions, uploading reference images. Specifically:
-    1. **Character Image**: Best in clean background, close-up, prominent subject, high-quality resolution.
-    2. **Character Description**: Brief, includes the subject and key appearance elements.
-<p align="center">
-<img src="./assets/dreamina_character.jpg" width=50% height=50% 
-class="center">
-</p>
-
-#### Step 2: Character-Driven Generation:
-Input prompts where the subject is replaced by the selected character, guiding the character to make corresponding changes such as style, actions, expressions, scenes, and modifiers. 
-There is no need to add descriptions of the subject in the prompt. "Face Reference Strength" is the weight for ID retention, and "Body Reference Strength" is the weight for IP retention.
-<p align="center">
-<img src="./assets/dreamina_generation.jpg" width=50% height=50% 
-class="center">
-</p>
-
 ##  Citation
 If you find this project useful for your research, please consider citing our papers:
 ```bibtex