Improve model card: Add pipeline_tag and enhance sample usage

README.md

@@ -1,13 +1,14 @@
 ---
-license: cc-by-nc-4.0
-language:
-- en
 base_model:
 - stabilityai/stable-diffusion-3-medium
+language:
+- en
 library_name: diffusers
-tags:
-- text-to-image
+license: cc-by-nc-4.0
+pipeline_tag: text-to-image
+tags: []
 ---
+
 # TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance (ICCV 2025)
 
 <p align="center"> 
@@ -27,14 +28,14 @@ TeEFusion is a simple yet powerful distillation method that fuses classifier-fre
 
 ## 🚀 Key Features
 
-* **Embed-Level Guidance Fusion**.  
-  Incorporates guidance magnitude *w* by linearly combining conditional and null prompt embeddings, eliminating the need for two forward passes .
+*   **Embed-Level Guidance Fusion**.  
+    Incorporates guidance magnitude *w* by linearly combining conditional and null prompt embeddings, eliminating the need for two forward passes .
 
-* **Test-Time Sampling Agnostic**.  
-  Distills from complex teacher sampling strategy (Euler + CFG, Z-Sampling + CFG, W2SD + CFG) into a simple student that uses standard Euler sampling .
+*   **Test-Time Sampling Agnostic**.  
+    Distills from complex teacher sampling strategy (Euler + CFG, Z-Sampling + CFG, W2SD + CFG) into a simple student that uses standard Euler sampling .
 
-* **Parameter-Free**.  
-  No extra network modules beyond the pretrained model’s encoder and decoder.
+*   **Parameter-Free**.  
+    No extra network modules beyond the pretrained model’s encoder and decoder.
 
 ---
 
@@ -56,7 +57,8 @@ from pipelines.sd3_teefusion_pipeline import TeEFusionSD3Pipeline
 
 pipe = TeEFusionSD3Pipeline.from_pretrained(
   "AIDC-AI/TeEFusion",
-  torch_dtype=torch.bfloat16
+  torch_dtype=torch.bfloat16,
+  trust_remote_code=True
 )
 pipe.to("cuda")