重新优化界面

app.py

@@ -24,7 +24,7 @@ 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
-
+from PIL import Image, ImageDraw, ImageFont
 
 def pil_to_binary_mask(pil_image, threshold=0):
     np_image = np.array(pil_image)
@@ -121,61 +121,53 @@ pipe = TryonPipeline.from_pretrained(
 )
 pipe.unet_encoder = UNet_Encoder
 
+progress=gr.Progress()
+
 @spaces.GPU
-def start_tryon(dict,garm_img,garment_des,is_checked,is_checked_crop,denoise_steps,seed):
+def infer(person,garment,denoise_steps,seed):
+    progress(0,desc="Starting")
     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")    
+    human_img = person.convert("RGB").resize((768,1024))
+    garm_img= garment.convert("RGB").resize((768,1024))
+    
+    progress(0.1,desc="Mask generating")
     
-    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))
-    else:
-        mask = pil_to_binary_mask(dict['layers'][0].convert("RGB").resize((768, 1024)))
-        # mask = transforms.ToTensor()(mask)
-        # mask = mask.unsqueeze(0)
+    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)
 
+    progress(0.3,desc="DensePose processing")
 
     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))
+
+    progress(0.5,desc="Image generating")
+
+    def callback(pipe, step, timestep, callback_kwargs):
+        progress_value = 0.5 + ((step+1.0)/denoise_steps)*(0.5/1.0)
+        progress(progress_value, desc=f"Image generating, {step + 1}/{denoise_steps} steps")
+        return callback_kwargs
     
     with torch.no_grad():
         # Extract the images
         with torch.cuda.amp.autocast():
             with torch.no_grad():
-                prompt = "model is wearing " + garment_des
+                prompt = "model is wearing clothing"
                 negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality"
                 with torch.inference_mode():
                     (
@@ -189,125 +181,117 @@ def start_tryon(dict,garm_img,garment_des,is_checked,is_checked_crop,denoise_ste
                         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 = "a photo of clothing"
+                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
-    # 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("## IDM-VTON 👕👔👚")
-    gr.Markdown("Virtual Try-on with your image and garment image. Check out the [source codes](https://github.com/yisol/IDM-VTON) and the [model](https://huggingface.co/yisol/IDM-VTON)")
+                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,
+                    callback_on_step_end=callback
+                )[0]
+    progress(1,desc="Complete")
+    return images[0]
+
+
+title = "## IDM-VTON"
+description = "Virtual Try-on with your image and garment image. Check out the [source codes](https://github.com/yisol/IDM-VTON) and the [model](https://huggingface.co/yisol/IDM-VTON)"
+
+example_path = os.path.join(os.path.dirname(__file__), 'example')
+person_list = os.listdir(os.path.join(example_path,"human"))
+person_images = [os.path.join(example_path,"human",person) for person in person_list]
+
+garment_list = os.listdir(os.path.join(example_path,"cloth"))
+garment_images = [os.path.join(example_path,"cloth",garment) for garment in garment_list]
+
+
+with gr.Blocks().queue() as demo:
+    gr.Markdown(title)
+    gr.Markdown(description)
     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)
+            gr.Markdown("#### Person Image")
+            person_image = gr.Image(
+                sources=["upload"],
+                type="pil",
+                label="Person Image",
+                width=512,
+                height=512,
+            )
 
-            example = gr.Examples(
-                inputs=imgs,
-                examples_per_page=10,
-                examples=human_ex_list
+            gr.Examples(
+                inputs=person_image,
+                examples_per_page=20,
+                examples=person_images,
+            )
+        with gr.Column():   
+            gr.Markdown("#### Garment Image")
+            garment_image = gr.Image(
+                sources=["upload"],
+                type="pil",
+                label="Garment Image",
+                width=512,
+                height=512,
             )
 
+            gr.Examples(
+                inputs=garment_image,
+                examples_per_page=20,
+                examples=garment_images,
+            )
         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)
-        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)
-
-
+            gr.Markdown("#### Generated Image")
 
+            gen_image = gr.Image(
+                label="Generated Image",
+                width=512,
+                height=512,
+            )
 
-    with gr.Column():
-        try_button = gr.Button(value="Try-on")
-        with gr.Accordion(label="Advanced Settings", open=False):
             with gr.Row():
+                gen_button = gr.Button("Generate")
+
+            with gr.Accordion("Advanced Options", open=False):
                 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,masked_img], api_name='tryon')
-
-            
-
-
-image_blocks.launch()
-
+        
+        gen_button.click(
+            fn=infer,
+            inputs=[person_image, garment_image, denoise_steps, seed], 
+            outputs=[gen_image]
+        )        
+
+demo.launch()