fix: out of memory error

app.py

@@ -34,11 +34,13 @@ if gr.NO_RELOAD:
 
     base.to("cuda")
     # refiner.to("cuda")
-    pipeline.to("cuda")
+    # pipeline.to("cuda")
 
     base.unet = torch.compile(base.unet, mode="reduce-overhead", fullgraph=True)
     # refiner.unet = torch.compile(refiner.unet, mode="reduce-overhead", fullgraph=True)
-    pipeline.unet = torch.compile(pipeline.unet, mode="reduce-overhead", fullgraph=True)
+    # pipeline.unet = torch.compile(pipeline.unet, mode="reduce-overhead", fullgraph=True)
+    pipeline.enable_model_cpu_offload()
+    pipeline.unet.enable_forward_chunking()
 
 def generate(prompt: str, progress=gr.Progress()):
     progress((0, 100), desc="Generating first frame...")