add arch-kd fig

docs/description.md

@@ -1,6 +1,7 @@
 This demo showcases a lightweight Stable Diffusion model (SDM) for general-purpose text-to-image synthesis. Our model **BK-SDM-Small** achieves **36% reduced** parameters and latency. This model is bulit with (i) removing several residual and attention blocks from the U-Net of SDM-v1.4 and (ii) distillation pretraining on only 0.22M LAION pairs (fewer than 0.1% of the full training set). Despite very limited training resources, our model can imitate the original SDM by benefiting from transferred knowledge.
 
 <center>
-    <img src="https://huggingface.co/spaces/nota-ai/compressed-stable-diffusion/blob/main/docs/fig_model.png" width="70%">
+    <img alt="U-Net architectures and KD-based pretraining" img src="https://huggingface.co/spaces/nota-ai/theme/resolve/3bb3eed8b911d0baf306767bb9548bf732052c53/docs/compressed_stable_diffusion/fig_model.png" width="70%">
 </center>
 
+<br/><br/>