Update app.py

app.py

@@ -1,5 +1,28 @@
-import spaces
+import os
+
+file_path = "/home/user/.pyenv/versions/3.10.16/lib/python3.10/site-packages/diffusers/utils/dynamic_modules_utils.py"
+if os.path.exists(file_path):
+    with open(file_path, "r") as f:
+        lines = f.readlines()
+
+    # Modify the import line
+    new_lines = []
+    for line in lines:
+        if "from huggingface_hub import cached_download" in line:
+            new_lines.append("from huggingface_hub import hf_hub_download, model_info\n")  # Remove cached_download
+        else:
+            new_lines.append(line)
+
+    # Write back the changes
+    with open(file_path, "w") as f:
+        f.writelines(new_lines)
+
+    print("Patched diffusers successfully!")
+else:
+    print("File not found:", file_path)
+
 import gradio as gr
+from diffusers.utils import load_image
 from PIL import Image
 from src.tryon_pipeline import StableDiffusionXLInpaintPipeline as TryonPipeline
 from src.unet_hacked_garmnet import UNet2DConditionModel as UNet2DConditionModel_ref
@@ -16,6 +39,7 @@ from typing import List
 import torch
 import os
 from transformers import AutoTokenizer
+import spaces
 import numpy as np
 from utils_mask import get_mask_location
 from torchvision import transforms
@@ -241,6 +265,126 @@ def start_tryon(dict,garm_img,garment_des,is_checked,is_checked_crop,denoise_ste
         return images[0], mask_gray
     # return images[0], mask_gray
 
+
+@spaces.GPU
+def start_tryon2(main_img_path, garm_img_path,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)
+
+    main_img = load_image(main_img_path)
+    garm_img = load_image(garm_img_path)
+
+    garm_img= garm_img.convert("RGB").resize((768,1024))
+    human_img_orig = main_img.convert("RGB")    
+    
+    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:
+        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))
+    
+    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'))
+    # 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 = "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
+    else:
+        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]
 
@@ -302,12 +446,21 @@ with image_blocks as demo:
                 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)
 
+    with gr.Column():
+        try_button2 = gr.Button(value="Try-on-experimental")
+        with gr.Row():
+            main_img_path = gr.Textbox(placeholder="main_img_path", show_label=False, elem_id="mainimgpath")
+            garm_img_path = gr.Textbox(placeholder="main_img_path", show_label=False, elem_id="garmimgpath")
+
+      
+
 
 
     try_button.click(fn=start_tryon, inputs=[imgs, garm_img, prompt, is_checked,is_checked_crop, denoise_steps, seed], outputs=[image_out,masked_img], api_name='tryon')
+    try_button2.click(fn=start_tryon2, inputs=[main_img_path, garm_img_path, prompt, is_checked,is_checked_crop, denoise_steps, seed], outputs=[image_out,masked_img], api_name='tryon2')
 
-            
 
+            
 
-image_blocks.launch()
 
+image_blocks.launch(show_error=True)