From a7cbcae1768e7158edb88bf41d61bc8982b741ba Mon Sep 17 00:00:00 2001
From: Lincoln Stein <lstein@gmail.com>
Date: Wed, 5 Jul 2023 20:59:14 -0400
Subject: [PATCH] expose max_cache_size to invokeai-configure interface

---
 invokeai/backend/install/invokeai_configure.py  | 17 +++++++----------
 .../backend/model_management/model_cache.py     | 14 ++------------
 2 files changed, 9 insertions(+), 22 deletions(-)

diff --git a/invokeai/backend/install/invokeai_configure.py b/invokeai/backend/install/invokeai_configure.py
index a0104bef25..0952a15cf7 100755
--- a/invokeai/backend/install/invokeai_configure.py
+++ b/invokeai/backend/install/invokeai_configure.py
@@ -430,13 +430,13 @@ to allow InvokeAI to download restricted styles & subjects from the "Concept Lib
             max_height=len(PRECISION_CHOICES) + 1,
             scroll_exit=True,
         )
-        self.max_loaded_models = self.add_widget_intelligent(
+        self.max_cache_size = self.add_widget_intelligent(
             IntTitleSlider,
-            name="Number of models to cache in CPU memory (each will use 2-4 GB!)",
-            value=old_opts.max_loaded_models,
-            out_of=10,
-            lowest=1,
-            begin_entry_at=4,
+            name="Size of the RAM cache used for fast model switching (GB)",
+            value=old_opts.max_cache_size,
+            out_of=20,
+            lowest=3,
+            begin_entry_at=6,
             scroll_exit=True,
         )
         self.nextrely += 1
@@ -539,7 +539,7 @@ https://huggingface.co/spaces/CompVis/stable-diffusion-license
                 "outdir",
                 "nsfw_checker",
                 "free_gpu_mem",
-                "max_loaded_models",
+                "max_cache_size",
                 "xformers_enabled",
                 "always_use_cpu",
         ]:
@@ -555,9 +555,6 @@ https://huggingface.co/spaces/CompVis/stable-diffusion-license
         new_opts.license_acceptance = self.license_acceptance.value
         new_opts.precision = PRECISION_CHOICES[self.precision.value[0]]
         
-        # widget library workaround to make max_loaded_models an int rather than a float
-        new_opts.max_loaded_models = int(new_opts.max_loaded_models)
-
         return new_opts
 
 
diff --git a/invokeai/backend/model_management/model_cache.py b/invokeai/backend/model_management/model_cache.py
index df5a2f9272..4155edb686 100644
--- a/invokeai/backend/model_management/model_cache.py
+++ b/invokeai/backend/model_management/model_cache.py
@@ -8,7 +8,7 @@ The cache returns context manager generators designed to load the
 model into the GPU within the context, and unload outside the
 context. Use like this:
 
-   cache = ModelCache(max_models_cached=6)
+   cache = ModelCache(max_cache_size=7.5)
    with cache.get_model('runwayml/stable-diffusion-1-5') as SD1,
           cache.get_model('stabilityai/stable-diffusion-2') as SD2:
        do_something_in_GPU(SD1,SD2)
@@ -91,7 +91,7 @@ class ModelCache(object):
         logger: types.ModuleType = logger
     ):
         '''
-        :param max_models: Maximum number of models to cache in CPU RAM [4]
+        :param max_cache_size: Maximum size of the RAM cache [6.0 GB]
         :param execution_device: Torch device to load active model into [torch.device('cuda')]
         :param storage_device: Torch device to save inactive model in [torch.device('cpu')]
         :param precision: Precision for loaded models [torch.float16]
@@ -126,16 +126,6 @@ class ModelCache(object):
             key += f":{submodel_type}"
         return key
 
-    #def get_model(
-    #    self,
-    #    repo_id_or_path: Union[str, Path],
-    #    model_type: ModelType = ModelType.Diffusers,
-    #    subfolder: Path = None,
-    #    submodel: ModelType = None,
-    #    revision: str = None,
-    #    attach_model_part: Tuple[ModelType, str] = (None, None),
-    #    gpu_load: bool = True,
-    #) -> ModelLocker:  # ?? what does it return
     def _get_model_info(
         self,
         model_path: str,