attempt to address memory issues when loading ckpt models (#2128)

- A couple of users have reported that switching back and forth
  between ckpt models is causing a "GPU out of memory" crash.
  Traceback suggests there is actually a CPU RAM issue.

- This speculative test simply performs a round of garbage collection
  before the point where the crash occurs.

ldm/invoke/model_cache.py

@@ -242,6 +242,9 @@ class ModelCache(object):
         # merged models from auto11 merge board are flat for some reason
         if 'state_dict' in sd:
             sd = sd['state_dict']
+
+        print(f'  | Forcing garbage collection prior to loading new model')
+        gc.collect()
         model = instantiate_from_config(omega_config.model)
         model.load_state_dict(sd, strict=False)