Upload diffusion checkpoint

README.md

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

diffusion.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0911a70d13fdeb0b20507332f14796b46b897262caaa7f5d5ce7aca7711ff33d
-size 3498240588
+oid sha256:2e08a4bbd081c1377a26404009ab45d7af816aa81b0cb130db5c818ae62b5ebc
+size 1758572077