Added normal simple sampler, updated lora finding again

src/load_lora_character.py

@@ -78,10 +78,8 @@ class LoadLoraCharacterNode:
             # Extract just the filenames for comparison
             lora_filenames = [path.split('\\')[-1] for path in lora_paths]
 
-            # Assume character_name is a string containing the character's name.
-            character_name_parts = character_name.lower().split()
-
-            # Assume lora_filenames is a list of filenames to search through.
+            character_name_lower = character_name.lower()
+            character_name_parts = character_name_lower.split()
             closest_match = None
             lowest_distance = float('inf')
 
@@ -89,10 +87,15 @@ class LoadLoraCharacterNode:
                 # Convert filename to lowercase for case-insensitive comparison.
                 filename_lower = filename.lower()
                 
-                # Check if any part of the character name is in the filename.
                 if any(part in filename_lower for part in character_name_parts):
-                    # Calculate the levenshtein distance for a closer match.
-                    total_distance = sum(self.levenshtein_distance(part, filename_lower) for part in character_name_parts)
+                    # Calculate the Levenshtein distance for the full character name as one of the metrics.
+                    full_name_distance = self.levenshtein_distance(character_name_lower, filename_lower)
+                    
+                    # Calculate the sum of distances for each part of the character name.
+                    parts_distance = sum(self.levenshtein_distance(part, filename_lower) for part in character_name_parts)
+                    
+                    # Use the minimum of full name distance and parts distance as the total distance.
+                    total_distance = min(full_name_distance, parts_distance)
                     print_sn0w("Distance: " + str(total_distance) + " Lora: " + filename)
 
                     if total_distance < lowest_distance:

src/simple_sampler.py

@@ -0,0 +1,67 @@
+from nodes import KSamplerAdvanced, VAEDecode, VAEEncode, EmptyLatentImage, ImageScaleBy, CLIPTextEncode
+from comfy_extras.nodes_upscale_model import ImageUpscaleWithModel
+import comfy.samplers
+
+class SimpleSamplerNode:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required":
+                    {"model": ("MODEL",),
+                    "clip": ("CLIP", ),
+                    "vae": ("VAE", ),
+                    "add_noise": (["enable", "disable"], ),
+                    "noise_seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
+                    "steps": ("INT", {"default": 20, "min": 1, "max": 10000}),
+                    "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01}),
+                    "width": ("INT", {"default": 0, "min": 0}),
+                    "height": ("INT", {"default": 0, "min": 0}),
+                    "sampler_name": (comfy.samplers.KSampler.SAMPLERS, ),
+                    "scheduler": (comfy.samplers.KSampler.SCHEDULERS, ),
+                    "positive": ("STRING", {"default": ""}),
+                    "negative": ("STRING", {"default": ""}),
+                    "start_at_step": ("INT", {"default": 0, "min": 0, "max": 10000}),
+                    "end_at_step": ("INT", {"default": 10000, "min": 0, "max": 10000}),
+                    "return_with_leftover_noise": (["disable", "enable"], ),
+                    "hires": ("BOOLEAN", {"default": False},),
+                    "upscale_model": ("UPSCALE_MODEL",),
+                    "hires_steps": ("INT", {"default": 5, "min": 1, "max": 20}),
+                     }
+                }
+
+    RETURN_TYPES = ("IMAGE", "CONDITIONING", "CONDITIONING")
+    RETURN_NAMES = ("IMAGE", "POSITIVE", "NEGATIVE")
+    FUNCTION = "sample"
+
+    CATEGORY = "sampling"
+
+    def sample(self, model, clip, vae, add_noise, noise_seed, steps, cfg, width, height, sampler_name, scheduler, positive, negative, start_at_step, end_at_step, return_with_leftover_noise, hires, upscale_model, hires_steps):
+        k_sampler_node = KSamplerAdvanced()
+        vae_decode = VAEDecode()
+        vae_encode = VAEEncode()
+        text_encode = CLIPTextEncode()
+        upscaler = ImageUpscaleWithModel()
+        scale_image = ImageScaleBy()
+
+        latent_image = EmptyLatentImage().generate(width, height)[0]
+
+        positive_prompt = text_encode.encode(clip, positive)[0]
+        negative_prompt = text_encode.encode(clip, negative)[0]
+
+        # Sampling
+        samples = k_sampler_node.sample(model, add_noise, noise_seed, steps, cfg, sampler_name, scheduler, positive_prompt, negative_prompt, latent_image, start_at_step, end_at_step, return_with_leftover_noise)[0]
+
+        if (hires):
+            # Decode the samples
+            image = vae_decode.decode(vae, samples)[0]
+
+            total_hires_steps = 25 - hires_steps
+            
+            upscaled_image = upscaler.upscale(upscale_model, image)[0]
+            upscaled_image = scale_image.upscale(upscaled_image, "nearest-exact", 0.5)[0]
+            upscaled_latent = vae_encode.encode(vae, upscaled_image)[0]
+            upscaled_samples = k_sampler_node.sample(model, add_noise, noise_seed, 25, cfg, sampler_name, scheduler, positive_prompt, negative_prompt, upscaled_latent, total_hires_steps, 1000, return_with_leftover_noise)[0]
+            image = vae_decode.decode(vae, upscaled_samples)
+        else:
+            image = vae_decode.decode(vae, samples)
+
+        return (image[0], positive_prompt, negative_prompt)