Update README.md

README.md

@@ -87,18 +87,26 @@ pipeline = VidXTendPipeline.from_pretrained(
   "benjamin-paine/vidxtend",
   torch_dtype=torch.float16,
   variant="fp16",
-).to("cuda", dtype=torch.float16)
+)
 ```
 
 Or, as a single file:
 
 ```py
-from aniportrait import VidXTendPipeline
+from vidxtend import VidXTendPipeline
 pipeline = VidXTendPipeline.from_single_file(
   "benjamin-paine/vidxtend",
   torch_dtype=torch.float16,
   variant="fp16",
-).to("cuda", dtype=torch.float16)
+)
+```
+
+Use these methods to improve performance:
+
+```
+pipeline.enable_model_cpu_offload()
+pipeline.enable_vae_slicing()
+pipeline.set_use_memory_efficient_attention_xformers()
 ```
 
 Usage is as follows: