Card: drop a redundant sentence

README.md

@@ -31,8 +31,7 @@ single DINOv3 pass instead of two.
   losses and VISReg). No posterior noise.
 - **Decoder:** a 4-block transformer trunk at width 1152 followed by a dense
   convolutional up-path, a slightly modernized VQGAN-like decoder (stride 16 to
-  full resolution, three residual blocks per level). One pass, no diffusion
-  sampling.
+  full resolution, three residual blocks per level).
 - **Training losses:** mainly a DINOv3-B feature loss on the reconstruction, with
   pixel and blurred-image MSE terms each at about a tenth of its gradient,
   following semantic_vae's DINO-loss-trained decoder.