checkpoint

py/nodes/lora_loader.py

@@ -8,7 +8,7 @@ from .utils import FlexibleOptionalInputType, any_type
 
 class LoraManagerLoader:
     NAME = "Lora Loader (LoraManager)"
-    CATEGORY = "loaders"
+    CATEGORY = "Lora Manager/loaders"
 
     @classmethod
     def INPUT_TYPES(cls):
@@ -23,7 +23,10 @@ class LoraManagerLoader:
                     "placeholder": "LoRA syntax input: <lora:name:strength>"
                 }),
             },
-            "optional": FlexibleOptionalInputType(any_type),
+            "optional": {
+                **FlexibleOptionalInputType(any_type),
+                "lora_stack": ("LORA_STACK", {"default": None}),
+            }
         }
 
     RETURN_TYPES = ("MODEL", "CLIP", IO.STRING)
@@ -49,11 +52,32 @@ class LoraManagerLoader:
                             return relative_path, trigger_words
         return lora_name, []  # Fallback if not found
 
-    def load_loras(self, model, clip, text, **kwargs):
-        """Loads multiple LoRAs based on the kwargs input."""
+    def extract_lora_name(self, lora_path):
+        """Extract the lora name from a lora path (e.g., 'IL\\aorunIllstrious.safetensors' -> 'aorunIllstrious')"""
+        # Get the basename without extension
+        basename = os.path.basename(lora_path)
+        return os.path.splitext(basename)[0]
+    
+    def load_loras(self, model, clip, text, lora_stack=None, **kwargs):
+        print("load_loras kwargs: ", kwargs)
+        """Loads multiple LoRAs based on the kwargs input and lora_stack."""
         loaded_loras = []
         all_trigger_words = []
         
+        # First process lora_stack if available
+        if lora_stack:
+            for lora_path, model_strength, clip_strength in lora_stack:
+                # Apply the LoRA using the provided path and strengths
+                model, clip = LoraLoader().load_lora(model, clip, lora_path, model_strength, clip_strength)
+                
+                # Extract lora name for trigger words lookup
+                lora_name = self.extract_lora_name(lora_path)
+                _, trigger_words = asyncio.run(self.get_lora_info(lora_name))
+                
+                all_trigger_words.extend(trigger_words)
+                loaded_loras.append(f"{lora_name}: {model_strength}")
+        
+        # Then process loras from kwargs
         if 'loras' in kwargs:
             for lora in kwargs['loras']:
                 if not lora.get('active', False):