Update README.md

README.md

@@ -1,8 +1,17 @@
+---
+license: mit
+library_name: diffusers
+tags:
+- text-to-image
+- safety-alignment
+- stable-diffusion
+- ECCV
+pipeline_tag: text-to-image
+---
 
 # SAGE: Structure-Aware Geometric Regularization (ECCV-26)
 
 **Paper:** The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models  
-**Venue:** ECCV 2026  
 **Authors:** Adeel Yousaf, Soumik Ghosh, James Beetham, Amrit Singh Bedi, Mubarak Shah  
 **Institution:** University of Central Florida  
 **Project Page:** [https://adeelyousaf.github.io/SAGE_ECCV26_Project_Page/](https://adeelyousaf.github.io/SAGE_ECCV26_Project_Page/)
@@ -11,21 +20,25 @@
 
 ## Overview
 
-We show that existing T2I safety alignment methods create an **illusion of high utility** — they appear to have high-utility preservation under coarse metrics (FID, CLIPScore) but suffer significant drops in fine-grained semantic fidelity (TIFA). We trace this to **semantic collapse** in the text encoder embedding space.
+We show that existing T2I safety alignment methods create an **illusion of high utility** — they appear to maintain high utility under coarse metrics (FID, CLIPScore) but suffer significant drops in fine-grained semantic fidelity (TIFA). We trace this to **semantic collapse** in the text encoder embedding space.
 
 **SAGE** is a geometry-aware safety alignment method that preserves embedding spread and local similarity structure during fine-tuning, achieving only a **−1.2% TIFA drop** vs. **−6.2% for DES** while maintaining strong safety (Avg. ASR 1.2%).
 
 ---
 
-## Model
-
-This is the fine-tuned **text encoder** of Stable Diffusion v1.4. The UNet remains frozen.
+## Use this Model
 
 ```python
 import torch
 from diffusers import StableDiffusionPipeline
+from huggingface_hub import hf_hub_download
 
+# Load base pipeline
 pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
-checkpoint = torch.load("SAGE.pt", map_location="cpu")
-pipe.text_encoder.load_state_dict(checkpoint)
+
+# Download and load SAGE text encoder weights
+ckpt_path = hf_hub_download(repo_id="Adeely93/SAGE", filename="SAGE.pt")
+pipe.text_encoder.load_state_dict(torch.load(ckpt_path, map_location="cpu"))
+
 pipe = pipe.to("cuda")
+image = pipe("a photo of a dog in a park").images[0]