Update readmie

README.md

@@ -42,11 +42,11 @@ Inspired by [In-Context-LoRA](https://github.com/ali-vilab/I
 > **_NOTE:_** This is a beta release of the model. The consistency between views may not be perfect, and the model might sometimes generate views that don't perfectly align or maintain exact object positions across viewpoints.
 
 
-# [FOUR-VIEWS]` 2 × 2-Grid LoRA
+# [FOUR-VIEWS-IMAGES] 2 × 2-Grid LoRA
 
 **Base:** FLUX-1-dev  
-**Images:** 126 custom composites  
-**Steps:** 800 (≈ 12.7 epochs)  
+**Images:** 126 custom image-text composites resized to 512x512 from [MVImgNET](https://github.com/GAP-LAB-CUHK-SZ/MVImgNet/tree/main)
+**Steps:** 100 (≈ 12.7 epochs)  
 **Rank:** 8  
 **Trigger token:**[FOUR-VIEWS];
 
@@ -60,7 +60,7 @@ pipeline = FluxPipeline.from_pretrained(
 )
 pipeline.load_lora_weights(
     "rmsandu/fourviews-incontext-lora",
-    weight_name="twoview-incontext-b03.safetensors",
+    weight_name="4views.safetensors",
 )
 pipeline.fuse_lora()