Update app-backup.py

app-backup.py

@@ -5,8 +5,7 @@ import logging
 import torch
 from PIL import Image
 import spaces
-from diffusers import DiffusionPipeline, AutoencoderTiny, AutoencoderKL, AutoPipelineForImage2Image, FluxControlNetModel
-from diffusers.pipelines import FluxControlNetPipeline
+from diffusers import DiffusionPipeline, AutoencoderTiny, AutoencoderKL, AutoPipelineForImage2Image
 from live_preview_helpers import calculate_shift, retrieve_timesteps, flux_pipe_call_that_returns_an_iterable_of_images
 from diffusers.utils import load_image
 from huggingface_hub import hf_hub_download, HfFileSystem, ModelCard, snapshot_download
@@ -21,7 +20,7 @@ import numpy as np
 import warnings
 
 
-huggingface_token = os.getenv("HUGGINFACE_TOKEN")
+huggingface_token = os.getenv("HF_TOKEN")
 
 
 translator = pipeline("translation", model="Helsinki-NLP/opus-mt-ko-en", device="cpu")
@@ -61,23 +60,6 @@ pipe_i2i = AutoPipelineForImage2Image.from_pretrained(
     torch_dtype=dtype
 ).to(device)
 
-# Upscale을 위한 ControlNet 설정
-controlnet = FluxControlNetModel.from_pretrained(
-    "jasperai/Flux.1-dev-Controlnet-Upscaler", torch_dtype=torch.bfloat16
-).to(device)
-
-# Upscale 파이프라인 설정 (기존 pipe 재사용)
-pipe_upscale = FluxControlNetPipeline(
-    vae=pipe.vae,
-    text_encoder=pipe.text_encoder,
-    text_encoder_2=pipe.text_encoder_2,
-    tokenizer=pipe.tokenizer,
-    tokenizer_2=pipe.tokenizer_2,
-    transformer=pipe.transformer,
-    scheduler=pipe.scheduler,
-    controlnet=controlnet
-).to(device)
-
 MAX_SEED = 2**32 - 1
 MAX_PIXEL_BUDGET = 1024 * 1024
 
@@ -118,25 +100,30 @@ def download_file(url, directory=None):
         file.write(response.content)
     
     return filepath
-            
+
 def update_selection(evt: gr.SelectData, selected_indices, loras_state, width, height):
     selected_index = evt.index
     selected_indices = selected_indices or []
     if selected_index in selected_indices:
         selected_indices.remove(selected_index)
     else:
-        if len(selected_indices) < 2:
+        if len(selected_indices) < 3:
             selected_indices.append(selected_index)
         else:
-            gr.Warning("You can select up to 2 LoRAs, remove one to select a new one.")
-            return gr.update(), gr.update(), gr.update(), selected_indices, gr.update(), gr.update(), width, height, gr.update(), gr.update()
+            gr.Warning("You can select up to 3 LoRAs, remove one to select a new one.")
+            return gr.update(), gr.update(), gr.update(), gr.update(), selected_indices, gr.update(), gr.update(), gr.update(), width, height, gr.update(), gr.update(), gr.update()
 
-    selected_info_1 = "Select a LoRA 1"
-    selected_info_2 = "Select a LoRA 2"
+    selected_info_1 = "Select LoRA 1"
+    selected_info_2 = "Select LoRA 2"
+    selected_info_3 = "Select LoRA 3"
+    
     lora_scale_1 = 1.15
     lora_scale_2 = 1.15
+    lora_scale_3 = 1.15    
     lora_image_1 = None
     lora_image_2 = None
+    lora_image_3 = None
+    
     if len(selected_indices) >= 1:
         lora1 = loras_state[selected_indices[0]]
         selected_info_1 = f"### LoRA 1 Selected: [{lora1['title']}](https://huggingface.co/{lora1['repo']}) ✨"
@@ -145,71 +132,78 @@ def update_selection(evt: gr.SelectData, selected_indices, loras_state, width, h
         lora2 = loras_state[selected_indices[1]]
         selected_info_2 = f"### LoRA 2 Selected: [{lora2['title']}](https://huggingface.co/{lora2['repo']}) ✨"
         lora_image_2 = lora2['image']
-
+    if len(selected_indices) >= 3:
+        lora3 = loras_state[selected_indices[2]]
+        selected_info_3 = f"### LoRA 3 Selected: [{lora3['title']}](https://huggingface.co/{lora3['repo']}) ✨"
+        lora_image_3 = lora3['image']
+        
     if selected_indices:
         last_selected_lora = loras_state[selected_indices[-1]]
         new_placeholder = f"Type a prompt for {last_selected_lora['title']}"
     else:
         new_placeholder = "Type a prompt after selecting a LoRA"
 
-    return gr.update(placeholder=new_placeholder), selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, width, height, lora_image_1, lora_image_2
-
-def remove_lora_1(selected_indices, loras_state):
-    if len(selected_indices) >= 1:
-        selected_indices.pop(0)
-    selected_info_1 = "Select a LoRA 1"
-    selected_info_2 = "Select a LoRA 2"
-    lora_scale_1 = 1.15
-    lora_scale_2 = 1.15
-    lora_image_1 = None
-    lora_image_2 = None
-    if len(selected_indices) >= 1:
-        lora1 = loras_state[selected_indices[0]]
-        selected_info_1 = f"### LoRA 1 Selected: [{lora1['title']}]({lora1['repo']}) ✨"
-        lora_image_1 = lora1['image']
-    if len(selected_indices) >= 2:
-        lora2 = loras_state[selected_indices[1]]
-        selected_info_2 = f"### LoRA 2 Selected: [{lora2['title']}]({lora2['repo']}) ✨"
-        lora_image_2 = lora2['image']
-    return selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, lora_image_1, lora_image_2
+    return gr.update(placeholder=new_placeholder), selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, width, height, lora_image_1, lora_image_2, lora_image_3
 
-def remove_lora_2(selected_indices, loras_state):
-    if len(selected_indices) >= 2:
-        selected_indices.pop(1)
+def remove_lora(selected_indices, loras_state, index_to_remove):
+    if len(selected_indices) > index_to_remove:
+        selected_indices.pop(index_to_remove)
+    
     selected_info_1 = "Select LoRA 1"
     selected_info_2 = "Select LoRA 2"
+    selected_info_3 = "Select LoRA 3"
     lora_scale_1 = 1.15
     lora_scale_2 = 1.15
+    lora_scale_3 = 1.15
     lora_image_1 = None
     lora_image_2 = None
-    if len(selected_indices) >= 1:
-        lora1 = loras_state[selected_indices[0]]
-        selected_info_1 = f"### LoRA 1 Selected: [{lora1['title']}]({lora1['repo']}) ✨"
-        lora_image_1 = lora1['image']
-    if len(selected_indices) >= 2:
-        lora2 = loras_state[selected_indices[1]]
-        selected_info_2 = f"### LoRA 2 Selected: [{lora2['title']}]({lora2['repo']}) ✨"
-        lora_image_2 = lora2['image']
-    return selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, lora_image_1, lora_image_2
+    lora_image_3 = None
+    
+    for i, idx in enumerate(selected_indices):
+        lora = loras_state[idx]
+        if i == 0:
+            selected_info_1 = f"### LoRA 1 Selected: [{lora['title']}]({lora['repo']}) ✨"
+            lora_image_1 = lora['image']
+        elif i == 1:
+            selected_info_2 = f"### LoRA 2 Selected: [{lora['title']}]({lora['repo']}) ✨"
+            lora_image_2 = lora['image']
+        elif i == 2:
+            selected_info_3 = f"### LoRA 3 Selected: [{lora['title']}]({lora['repo']}) ✨"
+            lora_image_3 = lora['image']
+    
+    return selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, lora_image_1, lora_image_2, lora_image_3
+
+def remove_lora_1(selected_indices, loras_state):
+    return remove_lora(selected_indices, loras_state, 0)
+
+def remove_lora_2(selected_indices, loras_state):
+    return remove_lora(selected_indices, loras_state, 1)
+
+def remove_lora_3(selected_indices, loras_state):
+    return remove_lora(selected_indices, loras_state, 2)
 
 def randomize_loras(selected_indices, loras_state):
     try:
-        if len(loras_state) < 2:
+        if len(loras_state) < 3:
             raise gr.Error("Not enough LoRAs to randomize.")
-        selected_indices = random.sample(range(len(loras_state)), 2)
+        selected_indices = random.sample(range(len(loras_state)), 3)
         lora1 = loras_state[selected_indices[0]]
         lora2 = loras_state[selected_indices[1]]
+        lora3 = loras_state[selected_indices[2]]
         selected_info_1 = f"### LoRA 1 Selected: [{lora1['title']}](https://huggingface.co/{lora1['repo']}) ✨"
         selected_info_2 = f"### LoRA 2 Selected: [{lora2['title']}](https://huggingface.co/{lora2['repo']}) ✨"
+        selected_info_3 = f"### LoRA 3 Selected: [{lora3['title']}](https://huggingface.co/{lora3['repo']}) ✨"
         lora_scale_1 = 1.15
         lora_scale_2 = 1.15
-        lora_image_1 = lora1['image']
-        lora_image_2 = lora2['image']
+        lora_scale_3 = 1.15
+        lora_image_1 = lora1.get('image', 'path/to/default/image.png')
+        lora_image_2 = lora2.get('image', 'path/to/default/image.png')
+        lora_image_3 = lora3.get('image', 'path/to/default/image.png')
         random_prompt = random.choice(prompt_values)
-        return selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, lora_image_1, lora_image_2, random_prompt
+        return selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, lora_image_1, lora_image_2, lora_image_3, random_prompt
     except Exception as e:
         print(f"Error in randomize_loras: {str(e)}")
-        return "Error", "Error", [], 1.15, 1.15, None, None, ""
+        return "Error", "Error", "Error", [], 1.15, 1.15, 1.15, 'path/to/default/image.png', 'path/to/default/image.png', 'path/to/default/image.png', ""
 
 def add_custom_lora(custom_lora, selected_indices, current_loras):
     if custom_lora:
@@ -234,18 +228,21 @@ def add_custom_lora(custom_lora, selected_indices, current_loras):
             # Update gallery
             gallery_items = [(item["image"], item["title"]) for item in current_loras]
             # Update selected_indices if there's room
-            if len(selected_indices) < 2:
+            if len(selected_indices) < 3:
                 selected_indices.append(existing_item_index)
             else:
-                gr.Warning("You can select up to 2 LoRAs, remove one to select a new one.")
+                gr.Warning("You can select up to 3 LoRAs, remove one to select a new one.")
 
             # Update selected_info and images
             selected_info_1 = "Select a LoRA 1"
             selected_info_2 = "Select a LoRA 2"
+            selected_info_3 = "Select a LoRA 3"
             lora_scale_1 = 1.15
             lora_scale_2 = 1.15
+            lora_scale_3 = 1.15
             lora_image_1 = None
             lora_image_2 = None
+            lora_image_3 = None
             if len(selected_indices) >= 1:
                 lora1 = current_loras[selected_indices[0]]
                 selected_info_1 = f"### LoRA 1 Selected: {lora1['title']} ✨"
@@ -254,24 +251,31 @@ def add_custom_lora(custom_lora, selected_indices, current_loras):
                 lora2 = current_loras[selected_indices[1]]
                 selected_info_2 = f"### LoRA 2 Selected: {lora2['title']} ✨"
                 lora_image_2 = lora2['image'] if lora2['image'] else None
+            if len(selected_indices) >= 3:
+                lora3 = current_loras[selected_indices[2]]
+                selected_info_3 = f"### LoRA 3 Selected: {lora3['title']} ✨"
+                lora_image_3 = lora3['image'] if lora3['image'] else None
             print("Finished adding custom LoRA")
             return (
                 current_loras,
                 gr.update(value=gallery_items),
                 selected_info_1, 
                 selected_info_2,
+                selected_info_3,
                 selected_indices,
                 lora_scale_1,
                 lora_scale_2,
+                lora_scale_3,
                 lora_image_1,
-                lora_image_2
+                lora_image_2,
+                lora_image_3
             )
         except Exception as e:
             print(e)
             gr.Warning(str(e))
-            return current_loras, gr.update(), gr.update(), gr.update(), selected_indices, gr.update(), gr.update(), gr.update(), gr.update()
+            return current_loras, gr.update(), gr.update(), gr.update(), gr.update(), selected_indices, gr.update(), gr.update(), gr.update(), gr.update(), gr.update(), gr.update()
     else:
-        return current_loras, gr.update(), gr.update(), gr.update(), selected_indices, gr.update(), gr.update(), gr.update(), gr.update()
+        return current_loras, gr.update(), gr.update(), gr.update(), gr.update(), selected_indices, gr.update(), gr.update(), gr.update(), gr.update(), gr.update(), gr.update()
 
 def remove_custom_lora(selected_indices, current_loras):
     if current_loras:
@@ -287,10 +291,13 @@ def remove_custom_lora(selected_indices, current_loras):
     # Update selected_info and images
     selected_info_1 = "Select a LoRA 1"
     selected_info_2 = "Select a LoRA 2"
+    selected_info_3 = "Select a LoRA 3"
     lora_scale_1 = 1.15
     lora_scale_2 = 1.15
+    lora_scale_3 = 1.15
     lora_image_1 = None
     lora_image_2 = None
+    lora_image_3 = None
     if len(selected_indices) >= 1:
         lora1 = current_loras[selected_indices[0]]
         selected_info_1 = f"### LoRA 1 Selected: [{lora1['title']}]({lora1['repo']}) ✨"
@@ -299,16 +306,23 @@ def remove_custom_lora(selected_indices, current_loras):
         lora2 = current_loras[selected_indices[1]]
         selected_info_2 = f"### LoRA 2 Selected: [{lora2['title']}]({lora2['repo']}) ✨"
         lora_image_2 = lora2['image']
+    if len(selected_indices) >= 3:
+        lora3 = current_loras[selected_indices[2]]
+        selected_info_3 = f"### LoRA 3 Selected: [{lora3['title']}]({lora3['repo']}) ✨"
+        lora_image_3 = lora3['image']
     return (
         current_loras,
         gr.update(value=gallery_items),
         selected_info_1,
         selected_info_2,
+        selected_info_3,
         selected_indices,
         lora_scale_1,
         lora_scale_2,
+        lora_scale_3,
         lora_image_1,
-        lora_image_2
+        lora_image_2,
+        lora_image_3
     )
 
 @spaces.GPU(duration=75)
@@ -350,9 +364,9 @@ def generate_image_to_image(prompt_mash, image_input_path, image_strength, steps
     ).images[0]
     return final_image
 
-def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_indices, lora_scale_1, lora_scale_2, randomize_seed, seed, width, height, loras_state, progress=gr.Progress(track_tqdm=True)):
+def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, randomize_seed, seed, width, height, loras_state, progress=gr.Progress(track_tqdm=True)):
     try:
-        # 한글 감지 및 번역
+        # 한글 감지 및 번역 (이 부분은 그대로 유지)
         if any('\u3131' <= char <= '\u318E' or '\uAC00' <= char <= '\uD7A3' for char in prompt):
             translated = translator(prompt, max_length=512)[0]['translation_text']
             print(f"Original prompt: {prompt}")
@@ -364,7 +378,7 @@ def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_ind
 
         selected_loras = [loras_state[idx] for idx in selected_indices]
 
-        # Build the prompt with trigger words
+        # Build the prompt with trigger words (이 부분은 그대로 유지)
         prepends = []
         appends = []
         for lora in selected_loras:
@@ -382,41 +396,52 @@ def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_ind
             pipe.unload_lora_weights()
             pipe_i2i.unload_lora_weights()
             
-        print(pipe.get_active_adapters())
+        print(f"Active adapters before loading: {pipe.get_active_adapters()}")
+        
         # Load LoRA weights with respective scales
         lora_names = []
         lora_weights = []
         with calculateDuration("Loading LoRA weights"):
             for idx, lora in enumerate(selected_loras):
-                lora_name = f"lora_{idx}"
-                lora_names.append(lora_name)
-                lora_weights.append(lora_scale_1 if idx == 0 else lora_scale_2)
-                lora_path = lora['repo']
-                weight_name = lora.get("weights")
-                print(f"Lora Path: {lora_path}")
-                if image_input is not None:
-                    if weight_name:
-                        pipe_i2i.load_lora_weights(lora_path, weight_name=weight_name, low_cpu_mem_usage=True, adapter_name=lora_name)
+                try:
+                    lora_name = f"lora_{idx}"
+                    lora_path = lora['repo']
+                    weight_name = lora.get("weights")
+                    print(f"Loading LoRA {lora_name} from {lora_path}")
+                    if image_input is not None:
+                        if weight_name:
+                            pipe_i2i.load_lora_weights(lora_path, weight_name=weight_name, adapter_name=lora_name)
+                        else:
+                            pipe_i2i.load_lora_weights(lora_path, adapter_name=lora_name)
                     else:
-                        pipe_i2i.load_lora_weights(lora_path, low_cpu_mem_usage=True, adapter_name=lora_name)
-                else:
-                    if weight_name:
-                        pipe.load_lora_weights(lora_path, weight_name=weight_name, low_cpu_mem_usage=True, adapter_name=lora_name)
-                    else:
-                        pipe.load_lora_weights(lora_path, low_cpu_mem_usage=True, adapter_name=lora_name)
+                        if weight_name:
+                            pipe.load_lora_weights(lora_path, weight_name=weight_name, adapter_name=lora_name)
+                        else:
+                            pipe.load_lora_weights(lora_path, adapter_name=lora_name)
+                    lora_names.append(lora_name)
+                    lora_weights.append(lora_scale_1 if idx == 0 else lora_scale_2 if idx == 1 else lora_scale_3)
+                except Exception as e:
+                    print(f"Failed to load LoRA {lora_name}: {str(e)}")
+
             print("Loaded LoRAs:", lora_names)
             print("Adapter weights:", lora_weights)
-            if image_input is not None:
-                pipe_i2i.set_adapters(lora_names, adapter_weights=lora_weights)
+            
+            if lora_names:
+                if image_input is not None:
+                    pipe_i2i.set_adapters(lora_names, adapter_weights=lora_weights)
+                else:
+                    pipe.set_adapters(lora_names, adapter_weights=lora_weights)
             else:
-                pipe.set_adapters(lora_names, adapter_weights=lora_weights)
-        print(pipe.get_active_adapters())
-        # Set random seed for reproducibility
+                print("No LoRAs were successfully loaded.")
+                return None, seed, gr.update(visible=False)
+
+        print(f"Active adapters after loading: {pipe.get_active_adapters()}")
+
+        # 여기서부터 이미지 생성 로직 (이 부분은 그대로 유지)
         with calculateDuration("Randomizing seed"):
             if randomize_seed:
                 seed = random.randint(0, MAX_SEED)
 
-        # Generate image
         if image_input is not None:
             final_image = generate_image_to_image(prompt_mash, image_input, image_strength, steps, cfg_scale, width, height, seed)
         else:
@@ -428,19 +453,16 @@ def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_ind
                 final_image = image
                 progress_bar = f'<div class="progress-container"><div class="progress-bar" style="--current: {step_counter}; --total: {steps};"></div></div>'
                 yield image, seed, gr.update(value=progress_bar, visible=True)
-            
-
 
         if final_image is None:
             raise Exception("Failed to generate image")
         
         return final_image, seed, gr.update(visible=False)
+
     except Exception as e:
         print(f"Error in run_lora: {str(e)}")
         return None, seed, gr.update(visible=False)
 
-
-
 run_lora.zerogpu = True
 
 def get_huggingface_safetensors(link):
@@ -524,119 +546,32 @@ css = '''
 footer {visibility: hidden;}
 '''
 
-# 업스케일 관련 함수 추가
-def process_input(input_image, upscale_factor, **kwargs):
-    w, h = input_image.size
-    w_original, h_original = w, h
-    aspect_ratio = w / h
-
-    was_resized = False
-
-    max_size = int(np.sqrt(MAX_PIXEL_BUDGET / (upscale_factor ** 2)))
-    if w > max_size or h > max_size:
-        if w > h:
-            w_new = max_size
-            h_new = int(w_new / aspect_ratio)
-        else:
-            h_new = max_size
-            w_new = int(h_new * aspect_ratio)
-        
-        input_image = input_image.resize((w_new, h_new), Image.LANCZOS)
-        was_resized = True
-        gr.Info(f"Input image resized to {w_new}x{h_new} to fit within pixel budget after upscaling.")
-
-    # resize to multiple of 8
-    w, h = input_image.size
-    w = w - w % 8
-    h = h - h % 8
-
-    return input_image.resize((w, h)), w_original, h_original, was_resized
-    
-from PIL import Image
-import numpy as np
-
-@spaces.GPU
-def infer_upscale(
-    seed,
-    randomize_seed,
-    input_image,
-    num_inference_steps,
-    upscale_factor,
-    controlnet_conditioning_scale,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if input_image is None:
-        return None, seed, gr.update(), gr.update(), gr.update(), gr.update(), gr.update(visible=True, value="Please upload an image for upscaling.")
-
-    try:
-        if randomize_seed:
-            seed = random.randint(0, MAX_SEED)
-        
-        input_image, w_original, h_original, was_resized = process_input(input_image, upscale_factor)
-
-        # rescale with upscale factor
-        w, h = input_image.size
-        control_image = input_image.resize((w * upscale_factor, h * upscale_factor), Image.LANCZOS)
-
-        generator = torch.Generator(device=device).manual_seed(seed)
-
-        gr.Info("Upscaling image...")
-        # 모든 텐서를 동일한 디바이스로 이동
-        pipe_upscale.to(device)
-        
-        # Ensure the image is in RGB format
-        if control_image.mode != 'RGB':
-            control_image = control_image.convert('RGB')
-        
-        # Convert to tensor and add batch dimension
-        control_image = torch.from_numpy(np.array(control_image)).permute(2, 0, 1).float().unsqueeze(0).to(device) / 255.0
-        
-        with torch.no_grad():
-            image = pipe_upscale(
-                prompt="",
-                control_image=control_image,
-                controlnet_conditioning_scale=controlnet_conditioning_scale,
-                num_inference_steps=num_inference_steps,
-                guidance_scale=3.5,
-                generator=generator,
-            ).images[0]
-
-        # Convert the image back to PIL Image
-        if isinstance(image, torch.Tensor):
-            image = image.cpu().permute(1, 2, 0).numpy()
-        
-        # Ensure the image data is in the correct range
-        image = np.clip(image * 255, 0, 255).astype(np.uint8)
-        image = Image.fromarray(image)
-
-        if was_resized:
-            gr.Info(
-                f"Resizing output image to targeted {w_original * upscale_factor}x{h_original * upscale_factor} size."
-            )
-            image = image.resize((w_original * upscale_factor, h_original * upscale_factor), Image.LANCZOS)
-
-        return image, seed, num_inference_steps, upscale_factor, controlnet_conditioning_scale, gr.update(), gr.update(visible=False)
-    except Exception as e:
-        print(f"Error in infer_upscale: {str(e)}")
-        import traceback
-        traceback.print_exc()
-        return None, seed, gr.update(), gr.update(), gr.update(), gr.update(), gr.update(visible=True, value=f"Error: {str(e)}")
-        
-def check_upscale_input(input_image, *args):
-    if input_image is None:
-        return gr.update(interactive=False), *args, gr.update(visible=True, value="Please upload an image for upscaling.")
-    return gr.update(interactive=True), *args, gr.update(visible=False)
-    
 with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, delete_cache=(60, 3600)) as app:
     loras_state = gr.State(loras)
     selected_indices = gr.State([])
     
+    gr.Markdown(
+        """
+        # MixGen3: 멀티 Lora(이미지 학습) 통합 생성 모델
+        
+        ### 사용 안내:
+        1) 갤러리에서 원하는 모델을 선택(최대 3개까지)
+        2) 프롬프트에 한글 또는 영문으로 원하는 내용을 입력
+        3) Generate 버튼 실행
+
+        ### Contacts: [email protected]        
+        """
+    )
+    
     with gr.Row():
         with gr.Column(scale=3):
             prompt = gr.Textbox(label="Prompt", lines=1, placeholder="Type a prompt after selecting a LoRA")
         with gr.Column(scale=1):
             generate_button = gr.Button("Generate", variant="primary", elem_classes=["button_total"])
-    
+
+
+
+
     with gr.Row(elem_id="loaded_loras"):
         with gr.Column(scale=1, min_width=25):
             randomize_button = gr.Button("🎲", variant="secondary", scale=1, elem_id="random_btn")
@@ -650,6 +585,7 @@ with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, delete_cache=(60, 3600)) as a
                     lora_scale_1 = gr.Slider(label="LoRA 1 Scale", minimum=0, maximum=3, step=0.01, value=1.15)
             with gr.Row():
                 remove_button_1 = gr.Button("Remove", size="sm")
+
         with gr.Column(scale=8):
             with gr.Row():
                 with gr.Column(scale=0, min_width=50):
@@ -660,6 +596,17 @@ with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, delete_cache=(60, 3600)) as a
                     lora_scale_2 = gr.Slider(label="LoRA 2 Scale", minimum=0, maximum=3, step=0.01, value=1.15)
             with gr.Row():
                 remove_button_2 = gr.Button("Remove", size="sm")
+
+        with gr.Column(scale=8):
+            with gr.Row():
+                with gr.Column(scale=0, min_width=50):
+                    lora_image_3 = gr.Image(label="LoRA 3 Image", interactive=False, min_width=50, width=50, show_label=False, show_share_button=False, show_download_button=False, show_fullscreen_button=False, height=50)
+                with gr.Column(scale=3, min_width=100):
+                    selected_info_3 = gr.Markdown("Select a LoRA 3")
+                with gr.Column(scale=5, min_width=50):
+                    lora_scale_3 = gr.Slider(label="LoRA 3 Scale", minimum=0, maximum=3, step=0.01, value=1.15)
+            with gr.Row():
+                remove_button_3 = gr.Button("Remove", size="sm")
     
     with gr.Row():
         with gr.Column():
@@ -698,85 +645,52 @@ with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, delete_cache=(60, 3600)) as a
                     randomize_seed = gr.Checkbox(True, label="Randomize seed")
                     seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0, randomize=True)
 
-# 업스케일 관련 UI 추가
-    with gr.Row():
-        upscale_button = gr.Button("Upscale", interactive=False)
-
-    with gr.Row():
-        with gr.Column(scale=4):
-            upscale_input = gr.Image(label="Input Image for Upscaling", type="pil")
-        with gr.Column(scale=1):
-            upscale_steps = gr.Slider(
-                label="Number of Inference Steps for Upscaling",
-                minimum=8,
-                maximum=50,
-                step=1,
-                value=28,
-            )
-            upscale_factor = gr.Slider(
-                label="Upscale Factor",
-                minimum=1,
-                maximum=4,
-                step=1,
-                value=4,
-            )
-            controlnet_conditioning_scale = gr.Slider(
-                label="Controlnet Conditioning Scale",
-                minimum=0.1,
-                maximum=1.0,
-                step=0.05,
-                value=0.5,  # 기본값을 0.5로 낮춤
-            )            
-            upscale_seed = gr.Slider(
-                label="Seed for Upscaling",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=42,
-            )
-            upscale_randomize_seed = gr.Checkbox(label="Randomize seed for Upscaling", value=True)
-            upscale_error = gr.Markdown(visible=False, value="Please provide an input image for upscaling.")
-    
-    with gr.Row():
-        upscale_result = gr.Image(label="Upscaled Image", type="pil")
-        upscale_seed_output = gr.Number(label="Seed Used", precision=0)
-
-
     gallery.select(
         update_selection,
         inputs=[selected_indices, loras_state, width, height],
-        outputs=[prompt, selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, width, height, lora_image_1, lora_image_2]
+        outputs=[prompt, selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, width, height, lora_image_1, lora_image_2, lora_image_3]
     )
+
     remove_button_1.click(
         remove_lora_1,
         inputs=[selected_indices, loras_state],
-        outputs=[selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, lora_image_1, lora_image_2]
+        outputs=[selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, lora_image_1, lora_image_2, lora_image_3]
     )
+    
     remove_button_2.click(
         remove_lora_2,
         inputs=[selected_indices, loras_state],
-        outputs=[selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, lora_image_1, lora_image_2]
+        outputs=[selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, lora_image_1, lora_image_2, lora_image_3]
     )
+    
+    remove_button_3.click(
+        remove_lora_3,
+        inputs=[selected_indices, loras_state],
+        outputs=[selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, lora_image_1, lora_image_2, lora_image_3]
+    )
+
     randomize_button.click(
         randomize_loras,
         inputs=[selected_indices, loras_state],
-        outputs=[selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, lora_image_1, lora_image_2, prompt]
+        outputs=[selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, lora_image_1, lora_image_2, lora_image_3, prompt]
     )
+
     add_custom_lora_button.click(
         add_custom_lora,
         inputs=[custom_lora, selected_indices, loras_state],
-        outputs=[loras_state, gallery, selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, lora_image_1, lora_image_2]
+        outputs=[loras_state, gallery, selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, lora_image_1, lora_image_2, lora_image_3]
     )
+
     remove_custom_lora_button.click(
         remove_custom_lora,
         inputs=[selected_indices, loras_state],
-        outputs=[loras_state, gallery, selected_info_1, selected_info_2, selected_indices, lora_scale_1, lora_scale_2, lora_image_1, lora_image_2]
+        outputs=[loras_state, gallery, selected_info_1, selected_info_2, selected_info_3, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, lora_image_1, lora_image_2, lora_image_3]
     )
 
     gr.on(
         triggers=[generate_button.click, prompt.submit],
         fn=run_lora,
-        inputs=[prompt, input_image, image_strength, cfg_scale, steps, selected_indices, lora_scale_1, lora_scale_2, randomize_seed, seed, width, height, loras_state],
+        inputs=[prompt, input_image, image_strength, cfg_scale, steps, selected_indices, lora_scale_1, lora_scale_2, lora_scale_3, randomize_seed, seed, width, height, loras_state],
         outputs=[result, seed, progress_bar]
     ).then(
         fn=lambda x, history: update_history(x, history) if x is not None else history,
@@ -784,48 +698,6 @@ with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, delete_cache=(60, 3600)) as a
         outputs=history_gallery,
     )
 
-    upscale_input.upload(
-        lambda x: gr.update(interactive=x is not None),
-        inputs=[upscale_input],
-        outputs=[upscale_button]
-    )
-    
-    upscale_error = gr.Markdown(visible=False, value="")
-
-    upscale_button.click(
-        infer_upscale,
-        inputs=[
-            upscale_seed,
-            upscale_randomize_seed,
-            upscale_input,
-            upscale_steps,
-            upscale_factor,
-            controlnet_conditioning_scale,
-        ],
-        outputs=[
-            upscale_result,
-            upscale_seed_output,
-            upscale_steps,
-            upscale_factor,
-            controlnet_conditioning_scale,
-            upscale_randomize_seed,
-            upscale_error
-        ],
-
-    ).then(
-        infer_upscale,
-        inputs=[
-        upscale_seed,
-            upscale_randomize_seed,
-            upscale_input,
-            upscale_steps,
-            upscale_factor,
-            controlnet_conditioning_scale,
-        ],
-        outputs=[upscale_result, upscale_seed_output]
-    )
-
-
 if __name__ == "__main__":
     app.queue(max_size=20)
     app.launch(debug=True)