img pron

app.py

@@ -148,6 +148,23 @@ pipeline_flux.load_lora_weights(
 )
 pipeline_flux.to("cuda", init_weight_dtype(args.mixed_precision))
 
+def print_image_info(img):
+    # Basic attributes
+    info = {
+        "Filename": img.filename,
+        "Format": img.format,
+        "Mode": img.mode,
+        "Size": img.size,
+        "Width": img.width,
+        "Height": img.height,
+        "DPI": img.info.get('dpi', "N/A"),
+        "Is Animated": getattr(img, "is_animated", False),
+        "Frames": getattr(img, "n_frames", 1)
+    }
+
+    print("----- Image Information -----")
+    for key, value in info.items():
+        print(f"{key}: {value}")
 
 def extract_frames(video_path):
     """
@@ -203,9 +220,9 @@ def process_video_frames(
     frames = extract_frames(video)
     
     processed_frames = []
-    
+    print(f"processed_frames {len(processed_frames)}")
     for person_image in frames:
-        new_result_image, result_image = submit_function_flux(
+        result_image = proc_function_vidfl(
             person_image,
             cloth_image,
         cloth_type,
@@ -214,12 +231,60 @@ def process_video_frames(
         seed,
         show_type
         )
+        print_image_info(result_image)
         yield result_image
         processed_frames.append(result_image)
     
     yield processed_frames
 
 
+@spaces.GPU(duration=120)
+def proc_function_vidfl(
+        person_image,
+        cloth_image,
+        cloth_type,
+        num_inference_steps,
+        guidance_scale,
+        seed,
+        show_type
+):
+
+
+    # Set random seed
+    generator = None
+    if seed != -1:
+        generator = torch.Generator(device='cuda').manual_seed(seed)
+
+    # Process input images
+    person_image = Image.open(person_image).convert("RGB")
+    cloth_image = Image.open(cloth_image).convert("RGB")
+
+    # Adjust image sizes
+    person_image = resize_and_crop(person_image, (args.width, args.height))
+    cloth_image = resize_and_padding(cloth_image, (args.width, args.height))
+
+    # Process mask
+
+    mask = automasker(
+        person_image,
+        cloth_type
+    )['mask']
+    mask = mask_processor.blur(mask, blur_factor=9)
+
+    # Inference
+    result_image = pipeline_flux(
+        image=person_image,
+        condition_image=cloth_image,
+        mask_image=mask,
+        width=args.width,
+        height=args.height,
+        num_inference_steps=num_inference_steps,
+        guidance_scale=guidance_scale,
+        generator=generator
+    ).images[0]
+
+    return result_image
+        
 @spaces.GPU(duration=120)
 def submit_function_flux(
         person_image,