Update README.md

README.md

@@ -1,3 +1,37 @@
----
-license: mit
----
+---
+license: mit
+---
+
+# Smoothed Energy Guidance for SDXL
+
+https://arxiv.org/abs/2408.00760 | https://colab.research.google.com/github/SusungHong/SEG-SDXL/blob/master/sdxl_seg.ipynb
+
+Identical to https://github.com/SusungHong/SEG-SDXL/blob/8d3b2007a5f0660f9dba110a5e83556395f7535f/pipeline_seg.py
+
+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).
+
+<p align="center">
+  <img src="teaser.jpg" width="90%">
+</p>
+
+## 🏔️ 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.
+
+**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="figures/seg_comparison.jpg" width="90%">
+
+ControlNet generation without prompts
+<img src="figures/seg_controlnet_comparison.jpg" width="90%">
+