Upload vae checkpoint

README.md

@@ -2,7 +2,7 @@
 license: mit
 tags:
   - tiny-stable-diffusion
-  - diffusion
+  - vae
   - image-generation
   - diffusion
 library_name: pytorch
@@ -10,15 +10,17 @@ library_name: pytorch
 
 # tiny-sd-models
 
-This is a **DIFFUSION** model trained with [tiny-stable-diffusion](https://github.com/your-username/tiny-stable-diffusion).
+This is a **VAE** model trained with [tiny-stable-diffusion](https://github.com/your-username/tiny-stable-diffusion).
 
 ## Model Description
 
-This is a Diffusion Transformer (DiT/MMDiT) trained for text-to-image generation in latent space.
+This is a Variational Autoencoder (VAE) trained to compress images into a latent space.
+The VAE follows the SD3 architecture with 16 latent channels and f8 compression ratio.
 
 ### Architecture
-- **Type**: DiT or MMDiT (Multi-Modal Diffusion Transformer)
-- **Conditioning**: CLIP text embeddings
+- **Type**: AutoencoderKL
+- **Latent Channels**: 16
+- **Compression**: f8 (64x64 → 8x8)
 
 ## Usage