Add --disable-smart-memory for those that want the old behaviour.

comfy/cli_args.py

@@ -82,6 +82,9 @@ vram_group.add_argument("--novram", action="store_true", help="When lowvram isn'
 vram_group.add_argument("--cpu", action="store_true", help="To use the CPU for everything (slow).")
 
 
+parser.add_argument("--disable-smart-memory", action="store_true", help="Force ComfyUI to agressively offload to regular ram instead of keeping models in vram when it can.")
+
+
 parser.add_argument("--dont-print-server", action="store_true", help="Don't print server output.")
 parser.add_argument("--quick-test-for-ci", action="store_true", help="Quick test for CI.")
 parser.add_argument("--windows-standalone-build", action="store_true", help="Windows standalone build: Enable convenient things that most people using the standalone windows build will probably enjoy (like auto opening the page on startup).")

comfy/model_management.py

@@ -202,6 +202,10 @@ if cpu_state == CPUState.MPS:
 
 print(f"Set vram state to: {vram_state.name}")
 
+DISABLE_SMART_MEMORY = args.disable_smart_memory
+
+if DISABLE_SMART_MEMORY:
+    print("Disabling smart memory management")
 
 def get_torch_device_name(device):
     if hasattr(device, 'type'):
@@ -289,7 +293,10 @@ def unload_model_clones(model):
 def free_memory(memory_required, device, keep_loaded=[]):
     unloaded_model = False
     for i in range(len(current_loaded_models) -1, -1, -1):
-        current_free_mem = get_free_memory(device)
+        if DISABLE_SMART_MEMORY:
+            current_free_mem = 0
+        else:
+            current_free_mem = get_free_memory(device)
         if current_free_mem > memory_required:
             break
         shift_model = current_loaded_models[i]