init readme

README.md

@@ -42,7 +42,7 @@ The training of the Taiyi-Diffusion-XL text-to-image model encompasses three mai
 Our machine evaluation involved a comprehensive comparison of various models. The evaluation metrics included CLIP Similarity (CLIP Sim), Inception Score (IS), and Fréchet Inception Distance (FID), providing a robust assessment of each model's performance in terms of image quality, diversity, and alignment with textual descriptions. In the English dataset (COCO), Taiyi-XL demonstrated superior performance across all metrics, achieving the highest scores in CLIP Sim, IS, and FID. This indicates Taiyi-XL's effectiveness in generating images closely aligned with English text prompts while maintaining high image quality and diversity. Similarly, in the Chinese dataset (COCO-CN), Taiyi-XL outperformed other models, showcasing its robust bilingual capabilities.
 
 
-#### Table: Zero-shot image-text retrieval results
+#### Table: Comparison of different models based on CLIP Sim, IS, and FID across English (COCO) and Chinese (COCO-CN) datasets
 
 | Model | CLIP Sim($\uparrow$) | FID($\downarrow$) | IS($\uparrow$) |
 |-------|----------------------|-------------------|----------------|