diff --git a/Nodes/Outputs.py b/Nodes/Outputs.py
index 3c04ff5..012f1c7 100644
--- a/Nodes/Outputs.py
+++ b/Nodes/Outputs.py
@@ -920,7 +920,7 @@ class PrimereAestheticCKPTScorer:
             },
         }
 
-    def aesthetic_scorer(self, image, get_aesthetic_score, add_to_checkpoint, add_to_saved_prompt, prompt, workflow_data = None, **kwargs):
+    def aesthetic_scorer(self, image, get_aesthetic_score, add_to_checkpoint, add_to_saved_prompt, prompt, dual_mode = True, workflow_data = None, **kwargs):
         final_prediction = '*** Aesthetic scorer off ***'
         models = []
         def pipe(model):
@@ -984,9 +984,13 @@ class PrimereAestheticCKPTScorer:
                     ae_model_access = os.path.join(AE_MODEL_ROOT, 'cafe_aesthetic')
                     style_model_access = os.path.join(AE_MODEL_ROOT, 'cafe_style')
                     if os.path.isdir(ae_model_access) == True and os.path.isdir(style_model_access) == True:
-                        models.append({"pipe": pipe(ae_model_access), "weights": [0.0, 1.0], })
-                        models.append({"pipe": pipe(style_model_access), "weights": [1.0, 0.75, 0.5, 0.0, 0.0], })
-
+                        if dual_mode == True:
+                            models.append({"pipe": pipe(ae_model_access), "weights": [0.0, 1.0], })
+                            models.append({"pipe": pipe(style_model_access), "weights": [1.0, 0.75, 0.5, 0.0, 0.0], })
+                            final_divider = 2
+                        else:
+                            models.append({"pipe": pipe(ae_model_access), "weights": [0.0, 1.0], })
+                            final_divider = 1
                         try:
                             count = 1
                             pil_images = image.permute(0, 3, 1, 2)
@@ -1007,7 +1011,7 @@ class PrimereAestheticCKPTScorer:
                                     scores[index] += sum(score) / w_sum
                             scores = sorted(scores.items(), key=lambda k: k[1], reverse=True)[:count]
                             final_score = ", ".join([f"{v:.3f}" for k, v in scores])
-                            final_prediction = int((float(final_score) * 1000) / 2)
+                            final_prediction = int((float(final_score) * 1000) / final_divider)
                         except Exception:
                             final_prediction = '*** Invalid input image ***'
                     else:
diff --git a/README.md b/README.md
index b6e55dd..17fafd6 100644
--- a/README.md
+++ b/README.md
@@ -50,7 +50,7 @@ The main difference between **minimal** and **basic** workflows, that **basic**
 
 - **Half-automatic model concept selector:**
   - **Supported concepts:** SD1, SD2, SDXL, SD3, StableCascade, Turbo, Flux, KwaiKolors, Hunyuan, Playground, Pony, LCM, Lightning, Hyper, PixartSigma, Sana (both 1024 and 512)
-  - Custom (and different) sampler settings for all concepts. The main ide that set sampler nodes only one time (`sampler`, `scheduler`, `step`, `cfg`) then just select model only what will use right sampler setting by `Model concept selector`. 
+  - Custom (and different) sampler settings for all concepts. The main idea is set sampler nodes only one time (`sampler`, `scheduler`, `step`, `cfg`) then just select model only what will use right sampler, vae, clip settings by `Model concept selector`. 
   - Auto detection of selected model type (if data already stored on external .json file, see longer [manual](Workflow/Manual/nodes/basic_workflow.md))
   - Auto **download** and apply Hyper, Lightning, and Turbo speed loras at first usage from here: https://huggingface.co/ByteDance/Hyper-SD/tree/main **check your SSD space before!**
 
diff --git a/Workflow/Manual/nodes/basic_production_plus_workflow.md b/Workflow/Manual/nodes/basic_production_plus_workflow.md
index 440eb29..602c8dc 100644
--- a/Workflow/Manual/nodes/basic_production_plus_workflow.md
+++ b/Workflow/Manual/nodes/basic_production_plus_workflow.md
@@ -15,13 +15,13 @@ This node allows you to enrich your prompts with various artistic styles, concep
 - Add multiple style elements to positive and negative prompts
 - Fine-tune the strength of each style component
 - Categories include:
- - Art Types (3d-rendering, digital-artwork, drawing, painting, photo, vector-art)
- - Concepts 
- - Artists
- - Art Movements
- - Colors
- - Directions
- - Moods
+- Art Types (3d-rendering, digital-artwork, drawing, painting, photo, vector-art)
+- Concepts 
+- Artists
+- Art Movements
+- Colors
+- Directions
+- Moods
 
 #### Style Controls:
 
@@ -37,11 +37,6 @@ Each category includes:
 - Stack multiple styles with precise control
 - Separate positive and negative style applications
 
-#### Node Outputs:
-
-- STYLE+: Enhanced positive prompt
-- STYLE-: Enhanced negative prompt
-
 <hr>
 
 ### Midjourney styles:
diff --git a/Workflow/Manual/nodes/montage_mj.jpg b/Workflow/Manual/nodes/montage_mj.jpg
index f1de829..61ca5d6 100644
Binary files a/Workflow/Manual/nodes/montage_mj.jpg and b/Workflow/Manual/nodes/montage_mj.jpg differ
diff --git a/components/detectors.py b/components/detectors.py
index 9ca72d1..fba3a9b 100644
--- a/components/detectors.py
+++ b/components/detectors.py
@@ -1465,8 +1465,11 @@ class DetailerForEach:
                         ae_model_access = os.path.join(AE_MODEL_ROOT, 'cafe_aesthetic')
                         style_model_access = os.path.join(AE_MODEL_ROOT, 'cafe_style')
                         if os.path.isdir(ae_model_access) == True and os.path.isdir(style_model_access) == True:
-                            original_score = int(Outputs.PrimereAestheticCKPTScorer.aesthetic_scorer(None, cropped_image, True, False, None, {})['result'][0])
-                            enhanced_score = int(Outputs.PrimereAestheticCKPTScorer.aesthetic_scorer(None, enhanced_image, True, False, None, {})['result'][0])
+                            try:
+                                original_score = int(Outputs.PrimereAestheticCKPTScorer.aesthetic_scorer(None, cropped_image, True, False, None, {}, False)['result'][0])
+                                enhanced_score = int(Outputs.PrimereAestheticCKPTScorer.aesthetic_scorer(None, enhanced_image, True, False, None, {}, False)['result'][0])
+                            except ImportError:
+                                use_aesthetic_scorer = False
                         else:
                             use_aesthetic_scorer = False
                     else: