Update README.md

README.md

@@ -20,7 +20,7 @@ diagonal Gaussian posterior.
 
 Trained with DINOv2 semantic alignment, this VAE was empirically found to
 offer comparable downstream diffusion convergence speed to other semantically
-aligned VAEs such as Flux.2 and PS-VAE v2, while being much faster to encode
+aligned VAEs such as Flux.2 and PS-VAE, while being much faster to encode
 and decode and achieving very high reconstruction quality (38.6 dB mean PSNR
 on 2k images).