Update README.md

README.md

@@ -2,8 +2,75 @@
 license: mit
 ---
 
-Project Page: https://yuemingpan.github.io/SFD.github.io/
+# Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
 
-Arxiv: https://arxiv.org/pdf/2512.04926
+## 🚩 Overview
+<p align="center">
+  <img src="https://raw.githubusercontent.com/yuemingPAN/SFD/main/images/teaser_v5.png" width="95%">
+</p>
+
+<div align="center" style="max-width:900px; text-align:justify; font-size:14px; line-height:1.5;">
+  <p>
+    <strong>(a) Overview of Semantic-First Diffusion (SFD).</strong>
+    Semantics (dashed curve) and textures (solid curve) follow asynchronous denoising trajectories.
+    SFD operates in three phases:
+    <span style="color:#d62728;">Stage I – Semantic initialization</span>, where semantic latents denoise first;
+    <span style="color:#4472c4;">Stage II – Asynchronous generation</span>, where semantics and textures denoise jointly but asynchronously, with semantics ahead of textures;
+    <span style="color:#2ca02c;">Stage III – Texture completion</span>, where only textures continue refining.
+    After denoising, the generated semantic latent <b>s₁</b> is discarded, and the final image is decoded solely from the texture latent <b>z₁</b>.
+    <strong>(b) Training convergence on ImageNet 256×256 without guidance.</strong>
+    SFD achieves substantially faster convergence than DiT-XL/2 and LightningDiT-XL/1 by approximately <b>100×</b> and <b>33.3×</b>, respectively.
+  </p>
+</div>
+
+---
+
+## ✨ Highlights
+- We propose **Semantic-First Diffusion (SFD)**, a novel latent diffusion paradigm that performs asynchronous denoising on semantic and texture latents, allowing semantics to denoise earlier and subsequently guide texture generation.  
+- **SFD achieves state-of-the-art FID score of 1.04** on ImageNet 256×256 generation.  
+- Exhibits **100×** and **33.3× faster** training convergence compared to **DiT** and **LightningDiT**, respectively.
+
+---
+
+## 🧪 Quantitative Results
+Explicitly **leading semantics ahead of textures with a moderate offset (Δt = 0.3)** achieves an optimal balance between early semantic stabilization and texture collaboration, effectively harmonizing their joint modeling.
+<p align="center">
+  <img src="https://raw.githubusercontent.com/yuemingPAN/SFD/main/images/fid_vs_delta_t.png" width="50%">
+</p>
+
+
+- On ImageNet 256×256, **SFD** achieves **FID 1.06** (LightningDiT-XL) and **FID 1.04** (1.0B LightningDiT-XXL).  
+- **100×** and **33.3×** faster training convergence compared to DiT and LightningDiT, respectively.
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/yuemingPAN/SFD/main/images/tabel.png" width="90%">
+</p>
+
+
+---
+
+## 🎨 Visual Results
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/yuemingPAN/SFD/main/images/demo_Sample.png" width="90%">
+</p>
+
+---
+
+## 🔗 Links
+- 🌐 **Project Page:** [https://yuemingpan.github.io/SFD.github.io/](https://yuemingpan.github.io/SFD.github.io/)
+- 📄 **Paper (arXiv):** [https://arxiv.org/pdf/2512.04926](https://arxiv.org/pdf/2512.04926)
+- 💾 **Code:** [https://github.com/yuemingPAN/SFD](https://github.com/yuemingPAN/SFD)
+- 🧰 **License:** MIT
+
+---
+
+## 🧩 Citation
+```bibtex
+@article{Pan2025SFD,
+  title={Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion},
+  author={Pan, Yueming and Feng, Ruoyu and Dai, Qi and Wang, Yuqi and Lin, Wenfeng and Guo, Mingyu and Luo, Chong and Zheng, Nanning},
+  journal={arXiv preprint arXiv:2512.04926},
+  year={2025}
+}
 
-Github: https://github.com/yuemingPAN/SFD