Update README.md

README.md

@@ -31,7 +31,7 @@ Our framework unifies three stages into an end-to-end pipeline:
 - Model Training — a memory-augmented Diffusion Transformer (DiT) with an error buffer that learns action-conditioned generation with memory-enhanced long-horizon consistency; 
 - Inference Deployment — few-step sampling, INT8 quantization, and model distillation achieving 720p@40FPS real-time generation with a 5B model.
 
-![Model Overview](./architecture.png)
+![Model Overview](./framework.png)
 
 ## ✨ Key Features
 - 🚀 **Feature 1**: **Upgraded Data Engine**: Combines Unreal Engine-based synthetic data, large-scale automated AAA game data, and real-world video augmentation to generate high-quality Video–Pose–Action–Prompt data.