Upload README.md with huggingface_hub

README.md

@@ -11,7 +11,9 @@ library_name: mdiffae
 
 # mdiffae_v1
 
-> **[mDiffAE v2](https://huggingface.co/data-archetype/mdiffae-v2) is now available and is the recommended version.** It offers substantially better reconstruction (+1.7 dB mean PSNR) with the same or better downstream convergence.
+> **DEPRECATED** — This model is superseded by [**SemDisDiffAE**](https://huggingface.co/data-archetype/semdisdiffae), which offers better reconstruction quality, better downstream diffusion convergence, and slightly faster inference.
+
+> **[mDiffAE v2](https://huggingface.co/data-archetype/mdiffae-v2) is also available but likewise superseded by SemDisDiffAE.** It offers substantially better reconstruction (+1.7 dB mean PSNR) with the same or better downstream convergence.
 >
 > | Version | Mean PSNR (2k images) | Bottleneck | Decoder |
 > |---|---|---|---|