Update README.md

README.md

@@ -3,5 +3,5 @@ license: apache-2.0
 ---
 # RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
 Detection Models:
-- Semantic Detector: Forensic-Chat, a generalizable and interpretable detector optimized from Qwen2.5-VL-7B. It assesses authenticity by analyzing image content (e.g., smooth greasy skin, artifacts in faces/hands, unnatural background blur).
-- Feature Detector: OmniAID achieves stable and accurate detection by being pre-trained on large-scale real and synthetic datasets. Feature-level artifacts are primarily associated with frequency artifacts and abnormal noise patterns.
+- **Semantic Detector**: Forensic-Chat, a generalizable and interpretable detector optimized from Qwen2.5-VL-7B. It assesses authenticity by analyzing image content (e.g., smooth greasy skin, artifacts in faces/hands, unnatural background blur).
+- **Feature Detector**: OmniAID achieves stable and accurate detection by being pre-trained on large-scale real and synthetic datasets. Feature-level artifacts are primarily associated with frequency artifacts and abnormal noise patterns.