Update README.md

README.md

@@ -4,7 +4,7 @@ datasets:
 language:
 - en
 ---
-# **Difix: Improving 3D Reconstructions with Single-Step Diffusion Models**  
+# **Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models**  
 CVPR 2025 (Oral)  
 [**Code**](https://github.com/nv-tlabs/Difix3D) | [**Project Page**](https://research.nvidia.com/labs/toronto-ai/difix3d/) | [**Paper**](https://arxiv.org/abs/2503.01774)
 
@@ -26,7 +26,7 @@ Difix is an all-encompassing solution, a single model compatible for both NeRF a
 
 **Model Developer:** NVIDIA
 
-**Model Versions:** Difix-SD-FP32
+**Model Versions:** difix_ref
 
 **Deployment Geography:** Global