Update app.py

app.py

@@ -1,5 +1,5 @@
-import spaces
 import gradio as gr
+import spaces
 from PIL import Image
 from src.tryon_pipeline import StableDiffusionXLInpaintPipeline as TryonPipeline
 from src.unet_hacked_garmnet import UNet2DConditionModel as UNet2DConditionModel_ref
@@ -16,7 +16,6 @@ from typing import List
 import torch
 import os
 from transformers import AutoTokenizer
-
 import numpy as np
 from utils_mask import get_mask_location
 from torchvision import transforms
@@ -26,6 +25,7 @@ from preprocess.openpose.run_openpose import OpenPose
 from detectron2.data.detection_utils import convert_PIL_to_numpy,_apply_exif_orientation
 from torchvision.transforms.functional import to_pil_image
 
+
 def pil_to_binary_mask(pil_image, threshold=0):
     np_image = np.array(pil_image)
     grayscale_image = Image.fromarray(np_image).convert("L")
@@ -39,53 +39,324 @@ def pil_to_binary_mask(pil_image, threshold=0):
     output_mask = Image.fromarray(mask)
     return output_mask
 
-import numpy as np
-from PIL import Image
 
+base_path = 'Roopansh/Ailusion-VTON-DEMO-v1.1'
+example_path = os.path.join(os.path.dirname(__file__), 'example')
+
+unet = UNet2DConditionModel.from_pretrained(
+    base_path,
+    subfolder="unet",
+    torch_dtype=torch.float16,
+)
+unet.requires_grad_(False)
+tokenizer_one = AutoTokenizer.from_pretrained(
+    base_path,
+    subfolder="tokenizer",
+    revision=None,
+    use_fast=False,
+)
+tokenizer_two = AutoTokenizer.from_pretrained(
+    base_path,
+    subfolder="tokenizer_2",
+    revision=None,
+    use_fast=False,
+)
+noise_scheduler = DDPMScheduler.from_pretrained(base_path, subfolder="scheduler")
+
+text_encoder_one = CLIPTextModel.from_pretrained(
+    base_path,
+    subfolder="text_encoder",
+    torch_dtype=torch.float16,
+)
+text_encoder_two = CLIPTextModelWithProjection.from_pretrained(
+    base_path,
+    subfolder="text_encoder_2",
+    torch_dtype=torch.float16,
+)
+image_encoder = CLIPVisionModelWithProjection.from_pretrained(
+    base_path,
+    subfolder="image_encoder",
+    torch_dtype=torch.float16,
+    )
+vae = AutoencoderKL.from_pretrained(base_path,
+                                    subfolder="vae",
+                                    torch_dtype=torch.float16,
+)
+
+# "stabilityai/stable-diffusion-xl-base-1.0",
+UNet_Encoder = UNet2DConditionModel_ref.from_pretrained(
+    base_path,
+    subfolder="unet_encoder",
+    torch_dtype=torch.float16,
+)
+
+parsing_model = Parsing(0)
+openpose_model = OpenPose(0)
+
+UNet_Encoder.requires_grad_(False)
+image_encoder.requires_grad_(False)
+vae.requires_grad_(False)
+unet.requires_grad_(False)
+text_encoder_one.requires_grad_(False)
+text_encoder_two.requires_grad_(False)
+tensor_transfrom = transforms.Compose(
+            [
+                transforms.ToTensor(),
+                transforms.Normalize([0.5], [0.5]),
+            ]
+    )
+
+pipe = TryonPipeline.from_pretrained(
+        base_path,
+        unet=unet,
+        vae=vae,
+        feature_extractor= CLIPImageProcessor(),
+        text_encoder = text_encoder_one,
+        text_encoder_2 = text_encoder_two,
+        tokenizer = tokenizer_one,
+        tokenizer_2 = tokenizer_two,
+        scheduler = noise_scheduler,
+        image_encoder=image_encoder,
+        torch_dtype=torch.float16,
+)
+pipe.unet_encoder = UNet_Encoder
 
-def get_mask_location(mode, category, parsing, keypoints):
-    parsing = np.array(parsing)
-    mask = np.zeros_like(parsing)
+@spaces.GPU(duration=120)
+def start_tryon(dict,garm_img,garment_des,is_checked,is_checked_crop,denoise_steps,seed):
+    device = "cuda"
     
-    print(f"Selected category: {category}")
-    print(f"Parsing shape: {parsing.shape}")
-    print(f"Unique values in parsing: {np.unique(parsing)}")
+    openpose_model.preprocessor.body_estimation.model.to(device)
+    pipe.to(device)
+    pipe.unet_encoder.to(device)
+
+    garm_img= garm_img.convert("RGB").resize((768,1024))
+    human_img_orig = dict["background"].convert("RGB")    
     
-    if category == "상의":
-        # 상의에 해당하는 부분만 마스킹 (상체, 팔)
-        upper_body = [5, 6, 7]
-        mask[np.isin(parsing, upper_body)] = 255
-        print(f"Masking upper body parts: {upper_body}")
-    elif category == "하의":
-        # 하의에 해당하는 부분만 마스킹 (하체)
-        lower_body = [9, 12, 13, 14, 15, 16, 17, 18, 19]
-        mask[np.isin(parsing, lower_body)] = 255
-        print(f"Masking lower body parts: {lower_body}")
-    elif category == "드레스":
-        # 드레스에 해당하는 부분 마스킹 (상체와 하체)
-        full_body = [5, 6, 7, 9, 12, 13, 14, 15, 16, 17, 18, 19]
-        mask[np.isin(parsing, full_body)] = 255
-        print(f"Masking full body parts: {full_body}")
+    if is_checked_crop:
+        width, height = human_img_orig.size
+        target_width = int(min(width, height * (3 / 4)))
+        target_height = int(min(height, width * (4 / 3)))
+        left = (width - target_width) / 2
+        top = (height - target_height) / 2
+        right = (width + target_width) / 2
+        bottom = (height + target_height) / 2
+        cropped_img = human_img_orig.crop((left, top, right, bottom))
+        crop_size = cropped_img.size
+        human_img = cropped_img.resize((768,1024))
     else:
-        raise ValueError(f"Unknown category: {category}")
-    
-    print(f"Mask shape: {mask.shape}, Unique values in mask: {np.unique(mask)}")
-    print(f"Number of masked pixels: {np.sum(mask == 255)}")
+        human_img = human_img_orig.resize((768,1024))
+
+
+    if is_checked:
+        keypoints = openpose_model(human_img.resize((384,512)))
+        model_parse, _ = parsing_model(human_img.resize((384,512)))
+        mask, mask_gray = get_mask_location('hd', "upper_body", model_parse, keypoints)
+        mask = mask.resize((768,1024))
+    else:
+        mask = pil_to_binary_mask(dict['layers'][0].convert("RGB").resize((768, 1024)))
+        # mask = transforms.ToTensor()(mask)
+        # mask = mask.unsqueeze(0)
+    mask_gray = (1-transforms.ToTensor()(mask)) * tensor_transfrom(human_img)
+    mask_gray = to_pil_image((mask_gray+1.0)/2.0)
+
+
+    human_img_arg = _apply_exif_orientation(human_img.resize((384,512)))
+    human_img_arg = convert_PIL_to_numpy(human_img_arg, format="BGR")
+     
     
-    # 마스크 시각화를 위한 코드 추가
-    import matplotlib.pyplot as plt
-    plt.figure(figsize=(10, 10))
-    plt.imshow(mask, cmap='gray')
-    plt.title(f"Mask for {category}")
-    plt.savefig(f"mask_{category}.png")
-    plt.close()
+
+    args = apply_net.create_argument_parser().parse_args(('show', './configs/densepose_rcnn_R_50_FPN_s1x.yaml', './ckpt/densepose/model_final_162be9.pkl', 'dp_segm', '-v', '--opts', 'MODEL.DEVICE', 'cuda'))
+    # verbosity = getattr(args, "verbosity", None)
+    pose_img = args.func(args,human_img_arg)    
+    pose_img = pose_img[:,:,::-1]    
+    pose_img = Image.fromarray(pose_img).resize((768,1024))
     
-    mask_gray = Image.fromarray(mask.astype(np.uint8))
-    return mask_gray, mask_gray
+    with torch.no_grad():
+        # Extract the images
+        with torch.cuda.amp.autocast():
+            with torch.no_grad():
+                prompt = "model is wearing " + garment_des
+                negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality"
+                with torch.inference_mode():
+                    (
+                        prompt_embeds,
+                        negative_prompt_embeds,
+                        pooled_prompt_embeds,
+                        negative_pooled_prompt_embeds,
+                    ) = pipe.encode_prompt(
+                        prompt,
+                        num_images_per_prompt=1,
+                        do_classifier_free_guidance=True,
+                        negative_prompt=negative_prompt,
+                    )
+                                    
+                    prompt = "a photo of " + garment_des
+                    negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality"
+                    if not isinstance(prompt, List):
+                        prompt = [prompt] * 1
+                    if not isinstance(negative_prompt, List):
+                        negative_prompt = [negative_prompt] * 1
+                    with torch.inference_mode():
+                        (
+                            prompt_embeds_c,
+                            _,
+                            _,
+                            _,
+                        ) = pipe.encode_prompt(
+                            prompt,
+                            num_images_per_prompt=1,
+                            do_classifier_free_guidance=False,
+                            negative_prompt=negative_prompt,
+                        )
+
+
+
+                    pose_img =  tensor_transfrom(pose_img).unsqueeze(0).to(device,torch.float16)
+                    garm_tensor =  tensor_transfrom(garm_img).unsqueeze(0).to(device,torch.float16)
+                    generator = torch.Generator(device).manual_seed(seed) if seed is not None else None
+                    images = pipe(
+                        prompt_embeds=prompt_embeds.to(device,torch.float16),
+                        negative_prompt_embeds=negative_prompt_embeds.to(device,torch.float16),
+                        pooled_prompt_embeds=pooled_prompt_embeds.to(device,torch.float16),
+                        negative_pooled_prompt_embeds=negative_pooled_prompt_embeds.to(device,torch.float16),
+                        num_inference_steps=denoise_steps,
+                        generator=generator,
+                        strength = 1.0,
+                        pose_img = pose_img.to(device,torch.float16),
+                        text_embeds_cloth=prompt_embeds_c.to(device,torch.float16),
+                        cloth = garm_tensor.to(device,torch.float16),
+                        mask_image=mask,
+                        image=human_img, 
+                        height=1024,
+                        width=768,
+                        ip_adapter_image = garm_img.resize((768,1024)),
+                        guidance_scale=2.0,
+                    )[0]
+
+    if is_checked_crop:
+        out_img = images[0].resize(crop_size)        
+        human_img_orig.paste(out_img, (int(left), int(top)))    
+        # return human_img_orig, mask_gray
+        return human_img_orig
+    else:
+        # return images[0], mask_gray
+        return images[0]
+    # return images[0], mask_gray
+
+garm_list = os.listdir(os.path.join(example_path,"cloth"))
+garm_list_path = [os.path.join(example_path,"cloth",garm) for garm in garm_list]
+
+human_list = os.listdir(os.path.join(example_path,"human"))
+human_list_path = [os.path.join(example_path,"human",human) for human in human_list]
+
+human_ex_list = []
+for ex_human in human_list_path:
+    ex_dict= {}
+    ex_dict['background'] = ex_human
+    ex_dict['layers'] = None
+    ex_dict['composite'] = None
+    human_ex_list.append(ex_dict)
+
+##default human
+
+
+image_blocks = gr.Blocks().queue()
+with image_blocks as demo:
+    # gr.Markdown("## AILUSION VTON DEMO 👕👔👚")
+    # gr.Markdown("Virtual Try-on with your image and garment image.")
     
+    with gr.Row():
+        with gr.Column():
+            imgs = gr.ImageEditor(sources='upload', type="pil", label='Human. Mask with pen or use auto-masking', interactive=True)
+            with gr.Row():
+                is_checked = gr.Checkbox(label="Yes", info="Use auto-generated mask (Takes 5 seconds)",value=True)
+            with gr.Row():
+                is_checked_crop = gr.Checkbox(label="Yes", info="Use auto-crop & resizing",value=False)
+            
+            with gr.Row(equal_height=True):
+                example = gr.Examples(
+                    inputs=imgs,
+                    examples_per_page=5,
+                    examples=human_ex_list
+                )
+
+        with gr.Column():
+            garm_img = gr.Image(label="Garment", sources='upload', type="pil")
+            with gr.Row(elem_id="prompt-container"):
+                with gr.Row():
+                    prompt = gr.Textbox(placeholder="Description of garment ex) Short Sleeve Round Neck T-shirts", show_label=False, elem_id="prompt")
+            example = gr.Examples(
+                inputs=garm_img,
+                examples_per_page=8,
+                examples=garm_list_path)
+        # with gr.Column():
+            # image_out = gr.Image(label="Output", elem_id="output-img", height=400)
+            # masked_img = gr.Image(label="Masked image output", elem_id="masked-img",show_share_button=False)
+        
+        # masked_img = ()
+        
+        with gr.Column():
+            # image_out = gr.Image(label="Output", elem_id="output-img", height=400)
+            image_out = gr.Image(label="Output", elem_id="output-img",show_share_button=False)
+
+    with gr.Column():
+        try_button = gr.Button(value="Try-on")
+        with gr.Accordion(label="Advanced Settings", open=False):
+            with gr.Row():
+                denoise_steps = gr.Number(label="Denoising Steps", minimum=20, maximum=40, value=30, step=1)
+                seed = gr.Number(label="Seed", minimum=-1, maximum=2147483647, step=1, value=42)
+
+
+
+    try_button.click(fn=start_tryon, inputs=[imgs, garm_img, prompt, is_checked,is_checked_crop, denoise_steps, seed], outputs=[image_out], api_name='tryon')
+
+            
+
+
+image_blocks.launch()
+import gradio as gr
+import spaces
+from PIL import Image
+from src.tryon_pipeline import StableDiffusionXLInpaintPipeline as TryonPipeline
+from src.unet_hacked_garmnet import UNet2DConditionModel as UNet2DConditionModel_ref
+from src.unet_hacked_tryon import UNet2DConditionModel
+from transformers import (
+    CLIPImageProcessor,
+    CLIPVisionModelWithProjection,
+    CLIPTextModel,
+    CLIPTextModelWithProjection,
+)
+from diffusers import DDPMScheduler,AutoencoderKL
+from typing import List
+
+import torch
+import os
+from transformers import AutoTokenizer
+import numpy as np
+from utils_mask import get_mask_location
+from torchvision import transforms
+import apply_net
+from preprocess.humanparsing.run_parsing import Parsing
+from preprocess.openpose.run_openpose import OpenPose
+from detectron2.data.detection_utils import convert_PIL_to_numpy,_apply_exif_orientation
+from torchvision.transforms.functional import to_pil_image
+
+
+def pil_to_binary_mask(pil_image, threshold=0):
+    np_image = np.array(pil_image)
+    grayscale_image = Image.fromarray(np_image).convert("L")
+    binary_mask = np.array(grayscale_image) > threshold
+    mask = np.zeros(binary_mask.shape, dtype=np.uint8)
+    for i in range(binary_mask.shape[0]):
+        for j in range(binary_mask.shape[1]):
+            if binary_mask[i,j] == True :
+                mask[i,j] = 1
+    mask = (mask*255).astype(np.uint8)
+    output_mask = Image.fromarray(mask)
+    return output_mask
 
 
-base_path = 'yisol/IDM-VTON'
+base_path = 'Roopansh/Ailusion-VTON-DEMO-v1.1'
 example_path = os.path.join(os.path.dirname(__file__), 'example')
 
 unet = UNet2DConditionModel.from_pretrained(
@@ -128,6 +399,7 @@ vae = AutoencoderKL.from_pretrained(base_path,
                                     torch_dtype=torch.float16,
 )
 
+# "stabilityai/stable-diffusion-xl-base-1.0",
 UNet_Encoder = UNet2DConditionModel_ref.from_pretrained(
     base_path,
     subfolder="unet_encoder",
@@ -165,17 +437,17 @@ pipe = TryonPipeline.from_pretrained(
 )
 pipe.unet_encoder = UNet_Encoder
 
-@spaces.GPU
-def start_tryon(dict, garm_img, garment_des, is_checked, is_checked_crop, denoise_steps, seed, category):
+@spaces.GPU(duration=120)
+def start_tryon(dict,garm_img,garment_des,is_checked,is_checked_crop,denoise_steps,seed):
     device = "cuda"
-
+    
     openpose_model.preprocessor.body_estimation.model.to(device)
     pipe.to(device)
     pipe.unet_encoder.to(device)
 
-    garm_img = garm_img.convert("RGB").resize((768,1024))
-    human_img_orig = dict["background"].convert("RGB")
-
+    garm_img= garm_img.convert("RGB").resize((768,1024))
+    human_img_orig = dict["background"].convert("RGB")    
+    
     if is_checked_crop:
         width, height = human_img_orig.size
         target_width = int(min(width, height * (3 / 4)))
@@ -191,72 +463,36 @@ def start_tryon(dict, garm_img, garment_des, is_checked, is_checked_crop, denois
         human_img = human_img_orig.resize((768,1024))
 
 
-    status_message = ""
     if is_checked:
-        try:
-            print(f"Processing category: {category}")
-            keypoints = openpose_model(human_img.resize((384,512)))
-            model_parse, _ = parsing_model(human_img.resize((384,512)))
-            
-            # 파싱 모델의 출력 확인
-            print(f"Parsing model output shape: {model_parse.shape}")
-            print(f"Unique values in parsing model output: {np.unique(model_parse)}")
-            
-            mask, mask_gray = get_mask_location('hd', category, model_parse, keypoints)
-            
-            # 마스크 확인 및 시각화
-            mask_array = np.array(mask)
-            print(f"Mask shape after get_mask_location: {mask_array.shape}")
-            print(f"Unique values in mask after get_mask_location: {np.unique(mask_array)}")
-            print(f"Number of masked pixels after get_mask_location: {np.sum(mask_array == 255)}")
-            
-            plt.figure(figsize=(10, 10))
-            plt.imshow(mask_array, cmap='gray')
-            plt.title(f"Mask after get_mask_location for {category}")
-            plt.savefig(f"mask_after_get_mask_location_{category}.png")
-            plt.close()
-            
-            mask = mask.resize((768,1024))
-            print(f"Mask created for category {category}")
-            
-            # 최종 마스크 확인
-            mask_array_final = np.array(mask)
-            print(f"Final mask shape: {mask_array_final.shape}")
-            print(f"Unique values in final mask: {np.unique(mask_array_final)}")
-            print(f"Number of masked pixels in final mask: {np.sum(mask_array_final == 255)}")
-            
-            plt.figure(figsize=(10, 10))
-            plt.imshow(mask_array_final, cmap='gray')
-            plt.title(f"Final Mask for {category}")
-            plt.savefig(f"final_mask_{category}.png")
-            plt.close()
-            
-        except Exception as e:
-            status_message = f"자동 마스크 생성 중 오류가 발생했습니다: {str(e)}. 기본 마스크를 사용합니다."
-            print(f"Error in mask creation: {str(e)}")
-            mask = Image.new('L', (768, 1024), 255)
+        keypoints = openpose_model(human_img.resize((384,512)))
+        model_parse, _ = parsing_model(human_img.resize((384,512)))
+        mask, mask_gray = get_mask_location('hd', "upper_body", model_parse, keypoints)
+        mask = mask.resize((768,1024))
     else:
-        if dict['layers'] and dict['layers'][0]:
-            mask = pil_to_binary_mask(dict['layers'][0].convert("RGB").resize((768, 1024)))
-        else:
-            mask = Image.new('L', (768, 1024), 255)
-    
+        mask = pil_to_binary_mask(dict['layers'][0].convert("RGB").resize((768, 1024)))
+        # mask = transforms.ToTensor()(mask)
+        # mask = mask.unsqueeze(0)
     mask_gray = (1-transforms.ToTensor()(mask)) * tensor_transfrom(human_img)
     mask_gray = to_pil_image((mask_gray+1.0)/2.0)
 
+
     human_img_arg = _apply_exif_orientation(human_img.resize((384,512)))
     human_img_arg = convert_PIL_to_numpy(human_img_arg, format="BGR")
+     
+    
 
     args = apply_net.create_argument_parser().parse_args(('show', './configs/densepose_rcnn_R_50_FPN_s1x.yaml', './ckpt/densepose/model_final_162be9.pkl', 'dp_segm', '-v', '--opts', 'MODEL.DEVICE', 'cuda'))
-    pose_img = args.func(args,human_img_arg)
-    pose_img = pose_img[:,:,::-1]
+    # verbosity = getattr(args, "verbosity", None)
+    pose_img = args.func(args,human_img_arg)    
+    pose_img = pose_img[:,:,::-1]    
     pose_img = Image.fromarray(pose_img).resize((768,1024))
-
+    
     with torch.no_grad():
+        # Extract the images
         with torch.cuda.amp.autocast():
             with torch.no_grad():
-                prompt = "((best quality, masterpiece, ultra-detailed, high quality photography, photo realistic)), the model is wearing " + garment_des
-                negative_prompt = "monochrome, lowres, bad anatomy, worst quality, normal quality, low quality, blurry, jpeg artifacts, sketch"
+                prompt = "model is wearing " + garment_des
+                negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality"
                 with torch.inference_mode():
                     (
                         prompt_embeds,
@@ -269,9 +505,9 @@ def start_tryon(dict, garm_img, garment_des, is_checked, is_checked_crop, denois
                         do_classifier_free_guidance=True,
                         negative_prompt=negative_prompt,
                     )
-
-                    prompt = "((best quality, masterpiece, ultra-detailed, high quality photography, photo realistic)), a photo of " + garment_des
-                    negative_prompt = "monochrome, lowres, bad anatomy, worst quality, normal quality, low quality, blurry, jpeg artifacts, sketch"
+                                    
+                    prompt = "a photo of " + garment_des
+                    negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality"
                     if not isinstance(prompt, List):
                         prompt = [prompt] * 1
                     if not isinstance(negative_prompt, List):
@@ -289,10 +525,12 @@ def start_tryon(dict, garm_img, garment_des, is_checked, is_checked_crop, denois
                             negative_prompt=negative_prompt,
                         )
 
+
+
                     pose_img =  tensor_transfrom(pose_img).unsqueeze(0).to(device,torch.float16)
                     garm_tensor =  tensor_transfrom(garm_img).unsqueeze(0).to(device,torch.float16)
                     generator = torch.Generator(device).manual_seed(seed) if seed is not None else None
-                    result = pipe(
+                    images = pipe(
                         prompt_embeds=prompt_embeds.to(device,torch.float16),
                         negative_prompt_embeds=negative_prompt_embeds.to(device,torch.float16),
                         pooled_prompt_embeds=pooled_prompt_embeds.to(device,torch.float16),
@@ -304,34 +542,22 @@ def start_tryon(dict, garm_img, garment_des, is_checked, is_checked_crop, denois
                         text_embeds_cloth=prompt_embeds_c.to(device,torch.float16),
                         cloth = garm_tensor.to(device,torch.float16),
                         mask_image=mask,
-                        image=human_img,
+                        image=human_img, 
                         height=1024,
                         width=768,
                         ip_adapter_image = garm_img.resize((768,1024)),
                         guidance_scale=2.0,
-                    )
-                    
-                    # 결과 형태 확인 및 처리
-                    if isinstance(result, tuple):
-                        images = result[0]
-                    elif hasattr(result, 'images'):
-                        images = result.images
-                    else:
-                        raise ValueError(f"Unexpected result type: {type(result)}")
-
-    print(f"Result type: {type(result)}")
-    print(f"Result content: {result}")
-    print(f"Mask shape: {mask.size}")
-    print(f"Human image shape: {human_img.size}")
-    print(f"Garment image shape: {garm_img.size}")
-    print(f"Output image shape: {images[0].size}")
+                    )[0]
 
     if is_checked_crop:
-        out_img = images[0].resize(crop_size)
-        human_img_orig.paste(out_img, (int(left), int(top)))
-        return human_img_orig, mask_gray, status_message
+        out_img = images[0].resize(crop_size)        
+        human_img_orig.paste(out_img, (int(left), int(top)))    
+        # return human_img_orig, mask_gray
+        return human_img_orig
     else:
-        return images[0], mask_gray, status_message
+        # return images[0], mask_gray
+        return images[0]
+    # return images[0], mask_gray
 
 garm_list = os.listdir(os.path.join(example_path,"cloth"))
 garm_list_path = [os.path.join(example_path,"cloth",garm) for garm in garm_list]
@@ -347,55 +573,64 @@ for ex_human in human_list_path:
     ex_dict['composite'] = None
     human_ex_list.append(ex_dict)
 
+##default human
+
+
 image_blocks = gr.Blocks(theme="Nymbo/Nymbo_Theme").queue(max_size=12)
+
 with image_blocks as demo:
-    with gr.Column():
-        try_button = gr.Button(value="가상 피팅 시작")
-        with gr.Accordion(label="고급 설정", open=False):
-            with gr.Row():
-                denoise_steps = gr.Number(label="디노이징 단계", minimum=20, maximum=40, value=30, step=1)
-                seed = gr.Number(label="시드", minimum=-1, maximum=2147483647, step=1, value=-1)
 
+    
     with gr.Row():
         with gr.Column():
-            imgs = gr.ImageEditor(sources='upload', type="pil", label='인물 사진. 펜으로 마스크 또는 자동 마스킹 사용', interactive=True)
+            imgs = gr.ImageEditor(sources='upload', type="pil", label='Human. Mask with pen or use auto-masking', interactive=True)
             with gr.Row():
-                is_checked = gr.Checkbox(label="예", info="자동 생성 마스크 사용 (5초 소요)",value=True)
+                is_checked = gr.Checkbox(label="Yes", info="Use auto-generated mask (Takes 5 seconds)",value=True)
             with gr.Row():
-                category = gr.Dropdown(
-                    choices=["상의", "하의", "드레스"],
-                    label="카테고리",
-                    value="상의"
+                is_checked_crop = gr.Checkbox(label="Yes", info="Use auto-crop & resizing",value=False)
+            
+            with gr.Row(equal_height=True):
+                example = gr.Examples(
+                    inputs=imgs,
+                    examples_per_page=5,
+                    examples=human_ex_list
                 )
-            with gr.Row():
-                is_checked_crop = gr.Checkbox(label="예", info="자동 자르기 및 크기 조정 사용",value=False)
-
-            example = gr.Examples(
-                inputs=imgs,
-                examples_per_page=15,
-                examples=human_ex_list
-            )
 
         with gr.Column():
-            garm_img = gr.Image(label="의류", sources='upload', type="pil")
+            garm_img = gr.Image(label="Garment", sources='upload', type="pil")
             with gr.Row(elem_id="prompt-container"):
                 with gr.Row():
-                    prompt = gr.Textbox(label="의류 설명", placeholder="반소매 라운드넥 티셔츠", show_label=True, elem_id="prompt")
+                    prompt = gr.Textbox(placeholder="Description of garment ex) Short Sleeve Round Neck T-shirts", show_label=False, elem_id="prompt")
             example = gr.Examples(
                 inputs=garm_img,
-                examples_per_page=16,
+                examples_per_page=8,
                 examples=garm_list_path)
-        with gr.Column():
-            masked_img = gr.Image(label="마스크 적용 이미지", elem_id="masked-img",show_share_button=False)
-        with gr.Column():
-            image_out = gr.Image(label="결과", elem_id="output-img",show_share_button=False)
+        # with gr.Column():
+            # image_out = gr.Image(label="Output", elem_id="output-img", height=400)
+            # masked_img = gr.Image(label="Masked image output", elem_id="masked-img",show_share_button=False)
         
+        # masked_img = ()
+        
+        with gr.Column():
+            # image_out = gr.Image(label="Output", elem_id="output-img", height=400)
+            image_out = gr.Image(label="Output", elem_id="output-img",show_share_button=False)
+
     with gr.Column():
-        status_message = gr.Textbox(label="상태", interactive=False)
+        try_button = gr.Button(value="Try-on")
+        with gr.Accordion(label="Advanced Settings", open=False):
+            with gr.Row():
+                denoise_steps = gr.Number(label="Denoising Steps", minimum=20, maximum=40, value=30, step=1)
+                seed = gr.Number(label="Seed", minimum=-1, maximum=2147483647, step=1, value=42)
+
+
+
+    try_button.click(fn=start_tryon, inputs=[imgs, garm_img, prompt, is_checked,is_checked_crop, denoise_steps, seed], outputs=[image_out], api_name='tryon')
+
+            
+
+
+
+
 
-    try_button.click(fn=start_tryon, 
-                     inputs=[imgs, garm_img, prompt, is_checked, is_checked_crop, denoise_steps, seed, category], 
-                     outputs=[image_out, masked_img, status_message], 
-                     api_name='tryon')
 
 image_blocks.launch(auth=("gini","pick"))