Add a /free route to unload models or free all memory.

A POST request to /free with: {"unload_models":true}
will unload models from vram.

A POST request to /free with: {"free_memory":true}
will unload models and free all cached data from the last run workflow.

main.py

@@ -97,7 +97,7 @@ def prompt_worker(q, server):
     gc_collect_interval = 10.0
 
     while True:
-        timeout = None
+        timeout = 1000.0
         if need_gc:
             timeout = max(gc_collect_interval - (current_time - last_gc_collect), 0.0)
 
@@ -118,6 +118,19 @@ def prompt_worker(q, server):
             execution_time = current_time - execution_start_time
             print("Prompt executed in {:.2f} seconds".format(execution_time))
 
+        flags = q.get_flags()
+        free_memory = flags.get("free_memory", False)
+
+        if flags.get("unload_models", free_memory):
+            comfy.model_management.unload_all_models()
+            need_gc = True
+            last_gc_collect = 0
+
+        if free_memory:
+            e.reset()
+            need_gc = True
+            last_gc_collect = 0
+
         if need_gc:
             current_time = time.perf_counter()
             if (current_time - last_gc_collect) > gc_collect_interval: