Update app.py

app.py

@@ -123,142 +123,25 @@ def pil_to_binary_mask(pil_image, threshold=0):
     output_mask = Image.fromarray(mask)
     return output_mask
 
-@spaces.GPU
-def start_tryon_full_body(tops_img, bottoms_img, model_parse_tops, model_parse_bottoms, 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)
-
-    # Convert and resize images
-    tops_img = tops_img.convert("RGB").resize((768, 1024))
-    bottoms_img = bottoms_img.convert("RGB").resize((768, 1024))
-
-    # Process tops image
-    human_img_orig_tops = model_parse_tops.convert("RGB").resize((768, 1024))
-    
-    if is_checked:
-        # Assuming mask creation for the tops
-        mask_tops, _ = get_mask_location('hd', "upper_body", model_parse_tops, {})
-        mask_tops = mask_tops.resize((768, 1024))
-    else:
-        mask_tops = pil_to_binary_mask(model_parse_tops.convert("RGB").resize((768, 1024)))
-
-    mask_gray_tops = (1 - transforms.ToTensor()(mask_tops)) * tensor_transfrom(human_img_orig_tops)
-    mask_gray_tops = to_pil_image((mask_gray_tops + 1.0) / 2.0)
-
-    human_img_arg_tops = _apply_exif_orientation(human_img_orig_tops.resize((384, 512)))
-    human_img_arg_tops = convert_PIL_to_numpy(human_img_arg_tops, 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_tops = args.func(args, human_img_arg_tops)
-    pose_img_tops = pose_img_tops[:, :, ::-1]
-    pose_img_tops = Image.fromarray(pose_img_tops).resize((768, 1024))
-
-    # Process bottoms image
-    human_img_orig_bottoms = model_parse_bottoms.convert("RGB").resize((768, 1024))
-    
-    if is_checked:
-        # Assuming mask creation for the bottoms
-        mask_bottoms, _ = get_mask_location('hd', "lower_body", model_parse_bottoms, {})
-        mask_bottoms = mask_bottoms.resize((768, 1024))
-    else:
-        mask_bottoms = pil_to_binary_mask(model_parse_bottoms.convert("RGB").resize((768, 1024)))
-
-    mask_gray_bottoms = (1 - transforms.ToTensor()(mask_bottoms)) * tensor_transfrom(human_img_orig_bottoms)
-    mask_gray_bottoms = to_pil_image((mask_gray_bottoms + 1.0) / 2.0)
-
-    human_img_arg_bottoms = _apply_exif_orientation(human_img_orig_bottoms.resize((384, 512)))
-    human_img_arg_bottoms = convert_PIL_to_numpy(human_img_arg_bottoms, format="BGR")
-
-    pose_img_bottoms = args.func(args, human_img_arg_bottoms)
-    pose_img_bottoms = pose_img_bottoms[:, :, ::-1]
-    pose_img_bottoms = Image.fromarray(pose_img_bottoms).resize((768, 1024))
-
-    with torch.no_grad():
-        with torch.cuda.amp.autocast():
-            prompt_tops = "model is wearing tops"
-            negative_prompt_tops = "monochrome, lowres, bad anatomy, worst quality, low quality"
-            prompt_bottoms = "model is wearing bottoms"
-            negative_prompt_bottoms = "monochrome, lowres, bad anatomy, worst quality, low quality"
-
-            # Encode prompts
-            (
-                prompt_embeds_tops,
-                negative_prompt_embeds_tops,
-                pooled_prompt_embeds_tops,
-                negative_pooled_prompt_embeds_tops,
-            ) = pipe.encode_prompt(
-                prompt_tops,
-                num_images_per_prompt=1,
-                do_classifier_free_guidance=True,
-                negative_prompt=negative_prompt_tops,
-            )
-
-            (
-                prompt_embeds_bottoms,
-                negative_prompt_embeds_bottoms,
-                pooled_prompt_embeds_bottoms,
-                negative_pooled_prompt_embeds_bottoms,
-            ) = pipe.encode_prompt(
-                prompt_bottoms,
-                num_images_per_prompt=1,
-                do_classifier_free_guidance=True,
-                negative_prompt=negative_prompt_bottoms,
-            )
-
-            pose_img_tops = tensor_transfrom(pose_img_tops).unsqueeze(0).to(device, torch.float16)
-            pose_img_bottoms = tensor_transfrom(pose_img_bottoms).unsqueeze(0).to(device, torch.float16)
-            garm_tensor_tops = tensor_transfrom(tops_img).unsqueeze(0).to(device, torch.float16)
-            garm_tensor_bottoms = tensor_transfrom(bottoms_img).unsqueeze(0).to(device, torch.float16)
-
-            generator = torch.Generator(device).manual_seed(seed) if seed is not None else None
-            images_tops = pipe(
-                prompt_embeds=prompt_embeds_tops.to(device, torch.float16),
-                negative_prompt_embeds=negative_prompt_embeds_tops.to(device, torch.float16),
-                pooled_prompt_embeds=pooled_prompt_embeds_tops.to(device, torch.float16),
-                negative_pooled_prompt_embeds=negative_pooled_prompt_embeds_tops.to(device, torch.float16),
-                num_inference_steps=denoise_steps,
-                generator=generator,
-                strength=1.0,
-                pose_img=pose_img_tops.to(device, torch.float16),
-                text_embeds_cloth=prompt_embeds_tops.to(device, torch.float16),
-                cloth=garm_tensor_tops.to(device, torch.float16),
-                mask_image=mask_tops,
-                image=human_img_orig_tops,
-                height=1024,
-                width=768,
-                ip_adapter_image=tops_img.resize((768, 1024)),
-                guidance_scale=2.0,
-            )[0]
-
-            images_bottoms = pipe(
-                prompt_embeds=prompt_embeds_bottoms.to(device, torch.float16),
-                negative_prompt_embeds=negative_prompt_embeds_bottoms.to(device, torch.float16),
-                pooled_prompt_embeds=pooled_prompt_embeds_bottoms.to(device, torch.float16),
-                negative_pooled_prompt_embeds=negative_pooled_prompt_embeds_bottoms.to(device, torch.float16),
-                num_inference_steps=denoise_steps,
-                generator=generator,
-                strength=1.0,
-                pose_img=pose_img_bottoms.to(device, torch.float16),
-                text_embeds_cloth=prompt_embeds_bottoms.to(device, torch.float16),
-                cloth=garm_tensor_bottoms.to(device, torch.float16),
-                mask_image=mask_bottoms,
-                image=human_img_orig_bottoms,
-                height=1024,
-                width=768,
-                ip_adapter_image=bottoms_img.resize((768, 1024)),
-                guidance_scale=2.0,
-            )[0]
-
-    # Combine images
-    combined_img = Image.new("RGB", (768, 2048))  # Height is 2x the original to accommodate both images
-    combined_img.paste(images_tops, (0, 0))
-    combined_img.paste(images_bottoms, (0, 1024))  # Paste bottoms image below tops
-
-    return combined_img, mask_gray_tops  # Or another mask, depending on your needs
 
+def decode_image_from_base64(base64_str):
+    try:
+        img_data = base64.b64decode(base64_str)
+        img = Image.open(BytesIO(img_data))
+        return img
+    except Exception as e:
+        logging.error(f"Error decoding image: {e}")
+        raise
 
+def encode_image_to_base64(img):
+    try:
+        buffered = BytesIO()
+        img.save(buffered, format="PNG")
+        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+        return img_str
+    except Exception as e:
+        logging.error(f"Error encoding image: {e}")
+        raise
 
 @spaces.GPU
 def start_tryon(dict, garm_img, garment_des, is_checked, is_checked_crop, denoise_steps, seed):
@@ -368,24 +251,7 @@ def start_tryon(dict, garm_img, garment_des, is_checked, is_checked_crop, denois
         return images[0], mask_gray
 
 
-def decode_image_from_base64(base64_str):
-    try:
-        img_data = base64.b64decode(base64_str)
-        img = Image.open(BytesIO(img_data))
-        return img
-    except Exception as e:
-        logging.error(f"Error decoding image: {e}")
-        raise
 
-def encode_image_to_base64(img):
-    try:
-        buffered = BytesIO()
-        img.save(buffered, format="PNG")
-        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
-        return img_str
-    except Exception as e:
-        logging.error(f"Error encoding image: {e}")
-        raise
 
 @app.route('/tryon', methods=['POST'])
 def tryon():
@@ -416,24 +282,167 @@ def tryon():
         'mask_image': mask_base64
     })
 
+
+def combine_images_with_masks(tops_image, bottoms_image, mask, is_checked_crop, crop_size):
+    try:
+        # Logique de combinaison des images de haut et de bas
+        if is_checked_crop:
+            tops_image = tops_image.resize(crop_size)
+            bottoms_image = bottoms_image.resize(crop_size)
+            combined_image = Image.new('RGB', (tops_image.width, tops_image.height))
+            combined_image.paste(tops_image, (0, 0))
+            combined_image.paste(bottoms_image, (0, tops_image.height // 2))
+        else:
+            combined_image = Image.new('RGB', (tops_image.width, tops_image.height))
+            combined_image.paste(tops_image, (0, 0))
+            combined_image.paste(bottoms_image, (0, tops_image.height // 2))
+
+        return combined_image
+
+    except Exception as e:
+        raise ValueError(f"Error combining images with masks: {e}")
+
+@spaces.GPU
+def start_tryon_full_body(tops_image, bottoms_image, model_parse_tops, model_parse_bottoms, is_checked, is_checked_crop, denoise_steps, seed):
+    try:
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+        openpose_model.preprocessor.body_estimation.model.to(device)
+        pipe.to(device)
+        pipe.unet_encoder.to(device)
+
+        # Traitement de l'image de haut (tops)
+        tops_image = tops_image.convert("RGB").resize((768, 1024))
+        human_img_orig = tops_image  # Utiliser l'image de haut comme arrière-plan
+
+        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', "full_body", model_parse, keypoints)
+            mask = mask.resize((768, 1024))
+        else:
+            mask = pil_to_binary_mask(model_parse_tops.convert("RGB").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'))
+        pose_img = args.func(args, human_img_arg)
+        pose_img = pose_img[:, :, ::-1]
+        pose_img = Image.fromarray(pose_img).resize((768, 1024))
+
+        # Traitement de l'image de bas (bottoms)
+        bottoms_image = bottoms_image.convert("RGB").resize((768, 1024))
+        bottoms_img_arg = _apply_exif_orientation(bottoms_image.resize((384, 512)))
+        bottoms_img_arg = convert_PIL_to_numpy(bottoms_img_arg, format="BGR")
+
+        # Combine les images de haut et de bas
+        combined_image = combine_images_with_masks(tops_image, bottoms_image, mask, is_checked_crop, crop_size)
+
+        with torch.no_grad():
+            with torch.cuda.amp.autocast():
+                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(combined_image).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=combined_image.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
+
+    except Exception as e:
+        raise ValueError(f"Error in start_tryon_full_body: {e}")
+
+
+
+
 @app.route('/tryon-full', methods=['POST'])
 def tryon_full():
     try:
         data = request.json
 
-        # Decode images
+        # Décoder les images
         tops_image = decode_image_from_base64(data['tops_image'])
         bottoms_image = decode_image_from_base64(data['bottoms_image'])
         model_parse_tops = decode_image_from_base64(data['model_parse_tops'])
         model_parse_bottoms = decode_image_from_base64(data['model_parse_bottoms'])
 
-        # Retrieve additional parameters
+        # Récupérer les paramètres supplémentaires
         is_checked = data.get('use_auto_mask', True)
         is_checked_crop = data.get('use_auto_crop', False)
         denoise_steps = int(data.get('denoise_steps', 30))
         seed = int(data.get('seed', 42))
 
-        # Call the start_tryon_full_body function
+        # Appeler la fonction principale
         output_image, mask_image = start_tryon_full_body(
             tops_image,
             bottoms_image,
@@ -445,7 +454,7 @@ def tryon_full():
             seed
         )
 
-        # Convert output image to base64
+        # Convertir les images en base64
         output_base64 = encode_image_to_base64(output_image)
         mask_base64 = encode_image_to_base64(mask_image)
 
@@ -453,10 +462,16 @@ def tryon_full():
             'output_image': output_base64,
             'mask_image': mask_base64
         })
-    
+
+    except KeyError as e:
+        logging.error(f"KeyError in /tryon-full: {e}")
+        return jsonify({'error': f"KeyError: {str(e)}"}), 400
+    except ValueError as e:
+        logging.error(f"ValueError in /tryon-full: {e}")
+        return jsonify({'error': f"ValueError: {str(e)}"}), 400
     except Exception as e:
         logging.error(f"Error in /tryon-full: {e}")
-        return jsonify({'error': str(e)}), 200
+        return jsonify({'error': f"Internal server error: {str(e)}"}), 500
 
 if __name__ == "__main__":
     app.run(debug=True, host="0.0.0.0", port=7860)