Update README.md

README.md

@@ -25,7 +25,7 @@ Our inference framework utilizes [lightx2v](https://github.com/ModelTC/lightx2v)
 The number of video segments (approximately 5 seconds each) can be adjusted by modifying the "num_fragments" parameter in the [configuration file](https://github.com/ModelTC/lightx2v/blob/main/configs/wan_t2v_causal.json). To perform autoregressive inference, simply specify the "lightx2v_path" and "model_path" in the [running script](https://github.com/ModelTC/lightx2v/blob/main/scripts/run_wan_t2v_causal.sh):
 
 ```bash
-bash scripts/run_wan_t2v_causal.sh
+bash scripts/run_wan_t2v_causvid_save_quant.sh
 ```
 
 ## License Agreement