Update README.md

README.md

@@ -31,8 +31,8 @@ If you want to train LoRAs based on Z-Image Turbo while maintaining its accelera
 This guide covers four different training approaches:
 - **Scheme 1**: Standard SFT Training + No Acceleration Configuration
 - **Scheme 2**: Differential LoRA Training + Acceleration Configuration
-- **Scheme 3**: Standard SFT + Trajectory Imitation Distillation
-- **Scheme 4**: Standard SFT + Loading DistillPatch LoRA (Recommended)
+- **Scheme 3**: Standard SFT + Trajectory Imitation Distillation + Acceleration Configuration
+- **Scheme 4**: Standard SFT + Loading DistillPatch LoRA (Recommended) + Acceleration Configuration
 
 We recommend **Scheme 4** as it offers the best trade-off between training simplicity and inference speed.