Update README.md

README.md

@@ -10,24 +10,22 @@ Identical to https://github.com/SusungHong/SEG-SDXL/blob/8d3b2007a5f0660f9dba110
 
 Implementation of [Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention](https://arxiv.org/abs/2408.00760) by [Susung Hong](https://susunghong.github.io).
 
-<img src="./teaser.jpg" width="90%">
+<img src="./teaser-2.jpg" width="90%">
 
 ## 🏔️ What is Smoothed Energy Guidance? How does it work?
 
-**Smoothed Energy Guidance (SEG)** is a training- and condition-free approach that leverages the energy-based perspective of the self-attention mechanism to improve image generation.
+Smoothed Energy Guidance (SEG) is a training- and condition-free approach that leverages the energy-based perspective of the self-attention mechanism to improve image generation.
 
-**Key points:**
+Key points:
 - Does not rely on the guidance scale parameter that causes side effects when the value becomes large
 - Allows continuous control of the original and maximally attenuated curvature of the energy landscape behind self-attention
 - Introduces a query blurring method, equivalent to blurring the entire attention weights without significant computational cost
 
-Please check **[our paper](https://arxiv.org/abs/2408.00760)** for details.
-
 ## 🔍 Comparison with other works
 
 SEG does not severely suffer from side effects such as making the overall image grayish or significantly changing the original structure, while improving generation quality even without prompts.
 
 Unconditional generation without prompts
-<img src="./seg_comparison.jpg" width="90%">
+<img src="./seg_comparison-2.jpg" width="90%">