Update README.md

README.md

@@ -16,10 +16,10 @@ base_model:
 # W8Yi/distilled-wsi-diffusion
 ![Teacher vs Student](./tile.png)
 
-`distilled-wsi-diffusion` is a distilled student model derived from PixCell for
+`distilled-wsi-diffusion` is a distilled student model derived from **PixCell** for
 UNI-conditioned histopathology image generation. It is designed to preserve the
 visual behavior of the PixCell teacher while enabling substantially faster
-sampling with fewer denoising steps, making it practical for rapid research
+sampling with fewer denoising steps(**7.06x** speed up), making it practical for rapid research
 iteration, hypothesis testing, and interpretability workflows on WSI features.
 
 ## Why Use This Model
@@ -104,13 +104,13 @@ img = decode_latents_to_images(pipeline, latents)[0]
 ![Teacher vs Student](./compare.png)
 
 Teacher rollout (35 steps): 0.8908s  
-Student rollout (4 steps): 0.1137s  
+Student rollout (4 steps): **0.1137s**  
 Teacher decode: 0.0147s  
-Student decode: 0.0145s  
+Student decode: **0.0145s**  
 Teacher total: 0.9055s  
-Student total: 0.1282s  
-Rollout speedup: 7.84x  
-End-to-end speedup: 7.06x  
+Student total: **0.1282s**  
+Rollout speedup: **7.84x**  
+End-to-end speedup: **7.06x**  
 
 Use the following snippet to reproduce side-by-side image and speedup numbers: