update for lower VRAM inference

README.md

@@ -91,7 +91,8 @@ pipe = LongCatImageEditPipeline.from_pretrained(
     transformer=transformer,
     text_processor=text_processor,
 )
-pipe.to(device, torch.bfloat16)
+# pipe.to(device, torch.bfloat16)  # Uncomment for high VRAM devices (Faster inference)
+pipe.enable_model_cpu_offload()  # Offload to CPU to save VRAM (Required ~19 GB); slower but prevents OOM
 
 generator = torch.Generator("cpu").manual_seed(43)
 img = Image.open('assets/test.png')