Update app.py

app.py

@@ -4,19 +4,10 @@ import json
 import logging
 import torch
 from PIL import Image
-from diffusers import (
-    DiffusionPipeline,
-    AutoencoderTiny,
-    AutoencoderKL,
-    AutoPipelineForImage2Image,
-    FluxControlNetModel,
-    FluxControlNetPipeline,
-)
-from live_preview_helpers import (
-    calculate_shift,
-    retrieve_timesteps,
-    flux_pipe_call_that_returns_an_iterable_of_images,
-)
+import spaces
+from diffusers import DiffusionPipeline, AutoencoderTiny, AutoencoderKL, AutoPipelineForImage2Image, FluxControlNetModel
+from diffusers.pipelines import FluxControlNetPipeline
+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
 import copy
@@ -25,13 +16,14 @@ import time
 import requests
 import pandas as pd
 from transformers import pipeline
-import warnings
 from gradio_imageslider import ImageSlider
+import numpy as np
+import warnings
 
 # 번역 모델 로드
 translator = pipeline("translation", model="Helsinki-NLP/opus-mt-ko-en")
 
-# Load prompts for randomization
+#Load prompts for randomization
 df = pd.read_csv('prompts.csv', header=None)
 prompt_values = df.values.flatten()
 
@@ -44,6 +36,16 @@ dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
 base_model = "black-forest-labs/FLUX.1-dev"
 
+huggingface_token = os.getenv("HUGGINFACE_TOKEN")
+
+model_path = snapshot_download(
+    repo_id="black-forest-labs/FLUX.1-dev", 
+    repo_type="model", 
+    ignore_patterns=["*.md", "*..gitattributes"],
+    local_dir="FLUX.1-dev",
+    token=huggingface_token, # type a new token-id.
+)
+
 taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device)
 good_vae = AutoencoderKL.from_pretrained(base_model, subfolder="vae", torch_dtype=dtype).to(device)
 pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=dtype, vae=taef1).to(device)
@@ -56,23 +58,16 @@ pipe_i2i = AutoPipelineForImage2Image.from_pretrained(
     text_encoder_2=pipe.text_encoder_2,
     tokenizer_2=pipe.tokenizer_2,
     torch_dtype=dtype
-).to(device)
+)
 
-# 업스케일링을 위한 ControlNet 모델 로드
+# Load controlnet for upscaling
 controlnet = FluxControlNetModel.from_pretrained(
-    "jasperai/Flux.1-dev-Controlnet-Upscaler", torch_dtype=dtype
+    "jasperai/Flux.1-dev-Controlnet-Upscaler", torch_dtype=torch.bfloat16
 ).to(device)
-
-pipe_controlnet = FluxControlNetPipeline(
-    vae=pipe.vae,
-    text_encoder=pipe.text_encoder,
-    tokenizer=pipe.tokenizer,
-    text_encoder_2=pipe.text_encoder_2,
-    tokenizer_2=pipe.tokenizer_2,
-    transformer=pipe.transformer,  # unet 대신 transformer 사용
-    controlnet=controlnet,
-    scheduler=pipe.scheduler
-).to(device)  # 'torch_dtype' 제거
+pipe_upscale = FluxControlNetPipeline.from_pretrained(
+    model_path, controlnet=controlnet, torch_dtype=torch.bfloat16
+)
+pipe_upscale.to(device)
 
 MAX_SEED = 2**32 - 1
 MAX_PIXEL_BUDGET = 1024 * 1024
@@ -98,23 +93,23 @@ class calculateDuration:
 def download_file(url, directory=None):
     if directory is None:
         directory = os.getcwd()  # Use current working directory if not specified
-
+    
     # Get the filename from the URL
     filename = url.split('/')[-1]
-
+    
     # Full path for the downloaded file
     filepath = os.path.join(directory, filename)
-
+    
     # Download the file
     response = requests.get(url)
     response.raise_for_status()  # Raise an exception for bad status codes
-
+    
     # Write the content to the file
     with open(filepath, 'wb') as file:
         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 []
@@ -222,7 +217,7 @@ def add_custom_lora(custom_lora, selected_indices, current_loras):
                 print(f"New LoRA: {new_item}")
                 existing_item_index = len(current_loras)
                 current_loras.append(new_item)
-
+            
             # Update gallery
             gallery_items = [(item["image"], item["title"]) for item in current_loras]
             # Update selected_indices if there's room
@@ -303,10 +298,11 @@ def remove_custom_lora(selected_indices, current_loras):
         lora_image_2
     )
 
+@spaces.GPU(duration=75)
 def generate_image(prompt_mash, steps, seed, cfg_scale, width, height, progress):
     print("Generating image...")
-    pipe.to(device)
-    generator = torch.Generator(device=device).manual_seed(seed)
+    pipe.to("cuda")
+    generator = torch.Generator(device="cuda").manual_seed(seed)
     with calculateDuration("Generating image"):
         # Generate image
         for img in pipe.flux_pipe_call_that_returns_an_iterable_of_images(
@@ -322,9 +318,10 @@ def generate_image(prompt_mash, steps, seed, cfg_scale, width, height, progress)
         ):
             yield img
 
+@spaces.GPU(duration=75)
 def generate_image_to_image(prompt_mash, image_input_path, image_strength, steps, cfg_scale, width, height, seed):
-    pipe_i2i.to(device)
-    generator = torch.Generator(device=device).manual_seed(seed)
+    pipe_i2i.to("cuda")
+    generator = torch.Generator(device="cuda").manual_seed(seed)
     image_input = load_image(image_input_path)
     final_image = pipe_i2i(
         prompt=prompt_mash,
@@ -370,7 +367,7 @@ def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_ind
     with calculateDuration("Unloading LoRA"):
         pipe.unload_lora_weights()
         pipe_i2i.unload_lora_weights()
-
+        
     print(pipe.get_active_adapters())
     # Load LoRA weights with respective scales
     lora_names = []
@@ -408,7 +405,7 @@ def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_ind
     # 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)
-        return final_image, seed, gr.update(visible=False)
+        yield final_image, seed, gr.update(visible=False)
     else:
         image_generator = generate_image(prompt_mash, steps, seed, cfg_scale, width, height, progress)
         # Consume the generator to get the final image
@@ -425,7 +422,7 @@ def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_ind
         
         yield final_image, seed, gr.update(value=progress_bar, visible=False)
 
-# run_lora.zerogpu = True  # 데코레이터 문제로 제거
+run_lora.zerogpu = True
 
 def get_huggingface_safetensors(link):
     split_link = link.split("/")
@@ -483,6 +480,31 @@ def update_history(new_image, history):
     history.insert(0, new_image)
     return history
 
+css = '''
+#gen_btn{height: 100%}
+#title{text-align: center}
+#title h1{font-size: 3em; display:inline-flex; align-items:center}
+#title img{width: 100px; margin-right: 0.25em}
+#gallery .grid-wrap{height: 5vh}
+#lora_list{background: var(--block-background-fill);padding: 0 1em .3em; font-size: 90%}
+.custom_lora_card{margin-bottom: 1em}
+.card_internal{display: flex;height: 100px;margin-top: .5em}
+.card_internal img{margin-right: 1em}
+.styler{--form-gap-width: 0px !important}
+#progress{height:30px}
+#progress .generating{display:none}
+.progress-container {width: 100%;height: 30px;background-color: #f0f0f0;border-radius: 15px;overflow: hidden;margin-bottom: 20px}
+.progress-bar {height: 100%;background-color: #4f46e5;width: calc(var(--current) / var(--total) * 100%);transition: width 0.5s ease-in-out}
+#component-8, .button_total{height: 100%; align-self: stretch;}
+#loaded_loras [data-testid="block-info"]{font-size:80%}
+#custom_lora_structure{background: var(--block-background-fill)}
+#custom_lora_btn{margin-top: auto;margin-bottom: 11px}
+#random_btn{font-size: 300%}
+#component-11{align-self: stretch;}
+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
@@ -494,8 +516,7 @@ def process_input(input_image, upscale_factor, **kwargs):
         warnings.warn(
             f"Requested output image is too large ({w * upscale_factor}x{h * upscale_factor}). Resizing to ({int(aspect_ratio * MAX_PIXEL_BUDGET ** 0.5 // upscale_factor), int(MAX_PIXEL_BUDGET ** 0.5 // aspect_ratio // upscale_factor)}) pixels."
         )
-        # Gradio does not have gr.Info, using print instead
-        print(
+        gr.Info(
             f"Requested output image is too large ({w * upscale_factor}x{h * upscale_factor}). Resizing input to ({int(aspect_ratio * MAX_PIXEL_BUDGET ** 0.5 // upscale_factor), int(MAX_PIXEL_BUDGET ** 0.5 // aspect_ratio // upscale_factor)}) pixels budget."
         )
         input_image = input_image.resize(
@@ -513,6 +534,7 @@ def process_input(input_image, upscale_factor, **kwargs):
 
     return input_image.resize((w, h)), w_original, h_original, was_resized
 
+@spaces.GPU
 def infer_upscale(
     seed,
     randomize_seed,
@@ -535,9 +557,8 @@ def infer_upscale(
 
     generator = torch.Generator().manual_seed(seed)
 
-    # Gradio does not have gr.Info, using print instead
-    print("Upscaling image...")
-    image = pipe_controlnet(
+    gr.Info("Upscaling image...")
+    image = pipe_upscale(
         prompt="",
         control_image=control_image,
         controlnet_conditioning_scale=controlnet_conditioning_scale,
@@ -549,64 +570,41 @@ def infer_upscale(
     ).images[0]
 
     if was_resized:
-        print(
+        gr.Info(
             f"Resizing output image to targeted {w_original * upscale_factor}x{h_original * upscale_factor} size."
         )
 
     # resize to target desired size
     image = image.resize((w_original * upscale_factor, h_original * upscale_factor))
     image.save("output.jpg")
-    # convert to PIL Image
-    return [true_input_image, image]
+    # convert to numpy
+    return [true_input_image, image, seed]
+
 
-css = '''
-#gen_btn{height: 100%}
-#title{text-align: center}
-#title h1{font-size: 3em; display:inline-flex; align-items:center}
-#title img{width: 100px; margin-right: 0.25em}
-#gallery .grid-wrap{height: 5vh}
-#lora_list{background: var(--block-background-fill);padding: 0 1em .3em; font-size: 90%}
-.custom_lora_card{margin-bottom: 1em}
-.card_internal{display: flex;height: 100px;margin-top: .5em}
-.card_internal img{margin-right: 1em}
-.styler{--form-gap-width: 0px !important}
-#progress{height:30px}
-#progress .generating{display:none}
-.progress-container {width: 100%;height: 30px;background-color: #f0f0f0;border-radius: 15px;overflow: hidden;margin-bottom: 20px}
-.progress-bar {height: 100%;background-color: #4f46e5;width: calc(var(--current) / var(--total) * 100%);transition: width 0.5s ease-in-out}
-#component-8, .button_total{height: 100%; align-self: stretch;}
-#loaded_loras [data-testid="block-info"]{font-size:80%}
-#custom_lora_structure{background: var(--block-background-fill)}
-#custom_lora_btn{margin-top: auto;margin-bottom: 11px}
-#random_btn{font-size: 300%}
-#component-11{align-self: stretch;}
-footer {visibility: hidden;}
-'''
 
 with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, delete_cache=(60, 3600)) as app:
 
     loras_state = gr.State(loras)
     selected_indices = gr.State([])
-
-    with gr.Tab("Generate"):
-        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")
-            with gr.Column(scale=8):
-                with gr.Row():
-                    with gr.Column(scale=0, min_width=50):
-                        lora_image_1 = gr.Image(label="LoRA 1 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_1 = gr.Markdown("Select a LoRA 1")
-                    with gr.Column(scale=5, min_width=50):
-                        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.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")
+        with gr.Column(scale=8):
+            with gr.Row():
+                with gr.Column(scale=0, min_width=50):
+                    lora_image_1 = gr.Image(label="LoRA 1 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_1 = gr.Markdown("Select a LoRA 1")
+                with gr.Column(scale=5, min_width=50):
+                    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):
@@ -617,102 +615,56 @@ 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.Row():
-            with gr.Column():
-                with gr.Group():
-                    with gr.Row(elem_id="custom_lora_structure"):
-                        custom_lora = gr.Textbox(label="Custom LoRA", info="LoRA Hugging Face path or *.safetensors public URL", placeholder="ginipick/flux-lora-eric-cat", scale=3, min_width=150)
-                        add_custom_lora_button = gr.Button("Add Custom LoRA", elem_id="custom_lora_btn", scale=2, min_width=150)
-                    remove_custom_lora_button = gr.Button("Remove Custom LoRA", visible=False)
-                    gr.Markdown("[Check the list of FLUX LoRAs](https://huggingface.co/models?other=base_model:adapter:black-forest-labs/FLUX.1-dev)", elem_id="lora_list")
-                gallery = gr.Gallery(
-                    [(item["image"], item["title"]) for item in loras],
-                    label="Or pick from the LoRA Explorer gallery",
-                    allow_preview=False,
-                    columns=4,
-                    elem_id="gallery"
-                )
+    with gr.Row():
+        with gr.Column():
+            with gr.Group():
+                with gr.Row(elem_id="custom_lora_structure"):
+                    custom_lora = gr.Textbox(label="Custom LoRA", info="LoRA Hugging Face path or *.safetensors public URL", placeholder="ginipick/flux-lora-eric-cat", scale=3, min_width=150)
+                    add_custom_lora_button = gr.Button("Add Custom LoRA", elem_id="custom_lora_btn", scale=2, min_width=150)
+                remove_custom_lora_button = gr.Button("Remove Custom LoRA", visible=False)
+                gr.Markdown("[Check the list of FLUX LoRAs](https://huggingface.co/models?other=base_model:adapter:black-forest-labs/FLUX.1-dev)", elem_id="lora_list")
+            gallery = gr.Gallery(
+                [(item["image"], item["title"]) for item in loras],
+                label="Or pick from the LoRA Explorer gallery",
+                allow_preview=False,
+                columns=4,
+                elem_id="gallery"
+            )
+        with gr.Column():
+            progress_bar = gr.Markdown(elem_id="progress", visible=False)
+            result = gr.Image(label="Generated Image", interactive=False)
+            with gr.Accordion("History", open=False):
+                history_gallery = gr.Gallery(label="History", columns=6, object_fit="contain", interactive=False)
+
+    
+    with gr.Row():
+        with gr.Accordion("Advanced Settings", open=False):
+            with gr.Row():
+                input_image = gr.Image(label="Input image", type="filepath")
+                image_strength = gr.Slider(label="Denoise Strength", info="Lower means more image influence", minimum=0.1, maximum=1.0, step=0.01, value=0.75)
             with gr.Column():
-                progress_bar = gr.Markdown(elem_id="progress", visible=False)
-                result = gr.Image(label="Generated Image", interactive=False)
-                with gr.Accordion("History", open=False):
-                    history_gallery = gr.Gallery(label="History", columns=6, object_fit="contain", interactive=False)
+                with gr.Row():
+                    cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, step=0.5, value=3.5)
+                    steps = gr.Slider(label="Steps", minimum=1, maximum=50, step=1, value=28)
 
-        with gr.Row():
-            with gr.Accordion("Advanced Settings", open=False):
                 with gr.Row():
-                    input_image = gr.Image(label="Input image", type="filepath")
-                    image_strength = gr.Slider(label="Denoise Strength", info="Lower means more image influence", minimum=0.1, maximum=1.0, step=0.01, value=0.75)
-                with gr.Column():
-                    with gr.Row():
-                        cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, step=0.5, value=3.5)
-                        steps = gr.Slider(label="Steps", minimum=1, maximum=50, step=1, value=28)
-
-                    with gr.Row():
-                        width = gr.Slider(label="Width", minimum=256, maximum=1536, step=64, value=1024)
-                        height = gr.Slider(label="Height", minimum=256, maximum=1536, step=64, value=1024)
-
-                    with gr.Row():
-                        randomize_seed = gr.Checkbox(True, label="Randomize seed")
-                        seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0, randomize=True)
-
-        # 이벤트 핸들러 설정
-        generate_button.click(
-            fn=run_lora,
-            inputs=[prompt, image_input, image_strength, cfg_scale, steps, selected_indices, lora_scale_1, lora_scale_2, randomize_seed, seed, width, height, loras_state],
-            outputs=[result, seed, progress_bar]
-        ).then(  # Update the history gallery
-            fn=lambda x, history: update_history(x, history),
-            inputs=[result, history_gallery],
-            outputs=history_gallery,
-        )
-        prompt.submit(
-            fn=run_lora,
-            inputs=[prompt, image_input, image_strength, cfg_scale, steps, selected_indices, lora_scale_1, lora_scale_2, randomize_seed, seed, width, height, loras_state],
-            outputs=[result, seed, progress_bar]
-        ).then(  # Update the history gallery
-            fn=lambda x, history: update_history(x, history),
-            inputs=[result, history_gallery],
-            outputs=history_gallery,
-        )
-        gallery.select(
-            fn=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]
-        )
-        remove_button_1.click(
-            fn=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]
-        )
-        remove_button_2.click(
-            fn=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]
-        )
-        randomize_button.click(
-            fn=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]
-        )
-        add_custom_lora_button.click(
-            fn=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]
-        )
-        remove_custom_lora_button.click(
-            fn=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]
-        )
+                    width = gr.Slider(label="Width", minimum=256, maximum=1536, step=64, value=1024)
+                    height = gr.Slider(label="Height", minimum=256, maximum=1536, step=64, value=1024)
 
-    with gr.Tab("Upscale"):
-        with gr.Row():
-            input_image_upscale = gr.Image(label="Input Image", type="pil")
-            result_upscale = ImageSlider(label="Input / Output", type="pil", interactive=True)
-        with gr.Row():
-            num_inference_steps_upscale = gr.Slider(
-                label="Number of Inference Steps",
+                with gr.Row():
+                    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")
+    
+    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,
@@ -732,34 +684,63 @@ with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, delete_cache=(60, 3600)) as a
                 step=0.1,
                 value=0.6,
             )
-            seed_upscale = gr.Slider(
-                label="Seed",
+            upscale_seed = gr.Slider(
+                label="Seed for Upscaling",
                 minimum=0,
                 maximum=MAX_SEED,
                 step=1,
                 value=42,
             )
-            randomize_seed_upscale = gr.Checkbox(label="Randomize seed", value=True)
-        with gr.Row():
-            upscale_button = gr.Button("Upscale", variant="primary")
-
-        # 업스케일 버튼 이벤트 핸들러
-        upscale_button.click(
-            fn=infer_upscale,
-            inputs=[
-                seed_upscale,
-                randomize_seed_upscale,
-                input_image_upscale,
-                num_inference_steps_upscale,
-                upscale_factor,
-                controlnet_conditioning_scale,
-            ],
-            outputs=result_upscale,
-        )
+            upscale_randomize_seed = gr.Checkbox(label="Randomize seed for Upscaling", value=True)
 
-app.queue()
-app.launch()
+    with gr.Row():
+        upscale_result = ImageSlider(label="Input / Output for Upscaling", type="pil", interactive=True)
 
 
+    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])
+    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]
+    )
+    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]
+    )
+    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]
+    )
+    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]
+    )
+    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]
+    )
+
+    gr.on(
+        [upscale_button.click],
+        fn=infer_upscale,
+        inputs=[
+            upscale_seed,
+            upscale_randomize_seed,
+            upscale_input,
+            upscale_steps,
+            upscale_factor,
+            controlnet_conditioning_scale,
+        ],
+        outputs=upscale_result,
+    )
 
 
+app.queue()
+app.launch()