Update README.md

README.md

@@ -39,12 +39,14 @@ Explicitly **leading semantics ahead of textures with a moderate offset (Δt = 0
 </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>
+### With AutoGuidance
+
+| Model   | Epochs | #Params | FID (NPU) |
+|:--------|:-------:|:--------:|:----------:|
+| SFD-XL  | 80      | 675M     | 1.30 |
+| SFD-XL  | 800     | 675M     | **1.06** |
+| SFD-XXL | 80      | 1.0B     | 1.19 |
+| SFD-XXL | 800     | 1.0B     | **1.04** |
 
 
 ---