added vid tab and fubncs

app.py

@@ -4,7 +4,7 @@ import os
 os.environ['CUDA_HOME'] = '/usr/local/cuda'
 os.environ['PATH'] = os.environ['PATH'] + ':/usr/local/cuda/bin'
 from datetime import datetime
-
+import cv2
 import gradio as gr
 import spaces
 import numpy as np
@@ -241,48 +241,85 @@ def submit_function(
     return new_result_image
 
 
-# @spaces.GPU(duration=120)
-# def submit_function_p2p(
-#         person_image,
-#         cloth_image,
-#         num_inference_steps,
-#         guidance_scale,
-#         seed):
-#     person_image = person_image["background"]
-# 
-#     tmp_folder = args.output_dir
-#     date_str = datetime.now().strftime("%Y%m%d%H%M%S")
-#     result_save_path = os.path.join(tmp_folder, date_str[:8], date_str[8:] + ".png")
-#     if not os.path.exists(os.path.join(tmp_folder, date_str[:8])):
-#         os.makedirs(os.path.join(tmp_folder, date_str[:8]))
-# 
-#     generator = None
-#     if seed != -1:
-#         generator = torch.Generator(device='cuda').manual_seed(seed)
-# 
-#     person_image = Image.open(person_image).convert("RGB")
-#     cloth_image = Image.open(cloth_image).convert("RGB")
-#     person_image = resize_and_crop(person_image, (args.width, args.height))
-#     cloth_image = resize_and_padding(cloth_image, (args.width, args.height))
-# 
-#     # Inference
-#     try:
-#         result_image = pipeline_p2p(
-#             image=person_image,
-#             condition_image=cloth_image,
-#             num_inference_steps=num_inference_steps,
-#             guidance_scale=guidance_scale,
-#             generator=generator
-#         )[0]
-#     except Exception as e:
-#         raise gr.Error(
-#             "An error occurred. Please try again later: {}".format(e)
-#         )
-# 
-#     # Post-process
-#     save_result_image = image_grid([person_image, cloth_image, result_image], 1, 3)
-#     save_result_image.save(result_save_path)
-#     return result_image
+
+def extract_frames(video_path):
+    """
+    Extract frames from a video file
+    
+    Args:
+        video_path (str): Path to the video file
+    
+    Returns:
+        list: List of frames as PIL Image objects
+    """
+    frames = []
+    cap = cv2.VideoCapture(video_path)
+    
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+        
+        # Convert OpenCV BGR to RGB
+        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        
+        # Convert to PIL Image
+        pil_image = Image.fromarray(frame_rgb)
+        frames.append(pil_image)
+    
+    cap.release()
+    return frames
+
+@spaces.GPU(duration=120)
+def process_video_frames(video, cloth_image, cloth_type, num_inference_steps, guidance_scale, seed, show_type):
+    """
+    Process each frame of the video through the flux pipeline
+    
+    Args:
+        video (str): Path to the input video file
+        cloth_image (str): Path to the cloth image
+        ... (other parameters from original function)
+    
+    Returns:
+        list: Processed frames
+    """
+    # Extract frames from video
+    frames = extract_frames(video)
+    
+    processed_frames = []
+    
+    for person_image in frames:
+        # Create a generator if seed is set
+        generator = None
+        if seed != -1:
+            generator = torch.Generator(device='cuda').manual_seed(seed)
+        
+        # Resize and process person image
+        person_image = resize_and_crop(person_image, (args.width, args.height))
+        
+        # Load and resize cloth image (do this outside the loop if it's constant)
+        cloth_image = Image.open(cloth_image).convert("RGB")
+        cloth_image = resize_and_padding(cloth_image, (args.width, args.height))
+        
+        # Generate mask (you might want to optimize this if mask is similar across frames)
+        mask = automasker(person_image, cloth_type)['mask']
+        mask = mask_processor.blur(mask, blur_factor=9)
+        
+        # Run 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]
+        
+        processed_frames.append(result_image)
+    
+    return processed_frames
 
 
 @spaces.GPU(duration=120)
@@ -359,7 +396,7 @@ def submit_function_flux(
         new_result_image = Image.new("RGB", (width + condition_width + 5, height))
         new_result_image.paste(conditions, (0, 0))
         new_result_image.paste(result_image, (condition_width + 5, 0))
-        return new_result_image, new_result_image
+        return new_result_image, result_image
 
 
 def person_example_fn(image_path):
@@ -654,124 +691,70 @@ def app_gradio():
                     result_image_flux,gal_output
                 )
 
-        # with gr.Tab("Mask-free & SD1.5"):
-        #     with gr.Row():
-        #         with gr.Column(scale=1, min_width=350):
-        #             with gr.Row():
-        #                 image_path_p2p = gr.Image(
-        #                     type="filepath",
-        #                     interactive=True,
-        #                     visible=False,
-        #                 )
-        #                 person_image_p2p = gr.ImageEditor(
-        #                     interactive=True, label="Person Image", type="filepath"
-        #                 )
-        # 
-        #             with gr.Row():
-        #                 with gr.Column(scale=1, min_width=230):
-        #                     cloth_image_p2p = gr.Image(
-        #                         interactive=True, label="Condition Image", type="filepath"
-        #                     )
-        # 
-        #             submit_p2p = gr.Button("Submit")
-        #             gr.Markdown(
-        #                 '<center><span style="color: #FF0000">!!! Click only Once, Wait for Delay !!!</span></center>'
-        #             )
-        # 
-        #             gr.Markdown(
-        #                 '<span style="color: #808080; font-size: small;">Advanced options can adjust details:<br>1. `Inference Step` may enhance details;<br>2. `CFG` is highly correlated with saturation;<br>3. `Random seed` may improve pseudo-shadow.</span>'
-        #             )
-        #             with gr.Accordion("Advanced Options", open=False):
-        #                 num_inference_steps_p2p = gr.Slider(
-        #                     label="Inference Step", minimum=10, maximum=100, step=5, value=50
-        #                 )
-        #                 # Guidence Scale
-        #                 guidance_scale_p2p = gr.Slider(
-        #                     label="CFG Strenth", minimum=0.0, maximum=7.5, step=0.5, value=2.5
-        #                 )
-        #                 # Random Seed
-        #                 seed_p2p = gr.Slider(
-        #                     label="Seed", minimum=-1, maximum=10000, step=1, value=42
-        #                 )
-        #                 # show_type = gr.Radio(
-        #                 #     label="Show Type",
-        #                 #     choices=["result only", "input & result", "input & mask & result"],
-        #                 #     value="input & mask & result",
-        #                 # )
-        # 
-        #         with gr.Column(scale=2, min_width=500):
-        #             result_image_p2p = gr.Image(interactive=False, label="Result")
-        #             with gr.Row():
-        #                 # Photo Examples
-        #                 root_path = "resource/demo/example"
-        #                 with gr.Column():
-        #                     gr.Examples(
-        #                         examples=[
-        #                             os.path.join(root_path, "person", "men", _)
-        #                             for _ in os.listdir(os.path.join(root_path, "person", "men"))
-        #                         ],
-        #                         examples_per_page=4,
-        #                         inputs=image_path_p2p,
-        #                         label="Person Examples ①",
-        #                     )
-        #                     gr.Examples(
-        #                         examples=[
-        #                             os.path.join(root_path, "person", "women", _)
-        #                             for _ in os.listdir(os.path.join(root_path, "person", "women"))
-        #                         ],
-        #                         examples_per_page=4,
-        #                         inputs=image_path_p2p,
-        #                         label="Person Examples ②",
-        #                     )
-        #                     gr.Markdown(
-        #                         '<span style="color: #808080; font-size: small;">*Person examples come from the demos of <a href="https://huggingface.co/spaces/levihsu/OOTDiffusion">OOTDiffusion</a> and <a href="https://www.outfitanyone.org">OutfitAnyone</a>. </span>'
-        #                     )
-        #                 with gr.Column():
-        #                     gr.Examples(
-        #                         examples=[
-        #                             os.path.join(root_path, "condition", "upper", _)
-        #                             for _ in os.listdir(os.path.join(root_path, "condition", "upper"))
-        #                         ],
-        #                         examples_per_page=4,
-        #                         inputs=cloth_image_p2p,
-        #                         label="Condition Upper Examples",
-        #                     )
-        #                     gr.Examples(
-        #                         examples=[
-        #                             os.path.join(root_path, "condition", "overall", _)
-        #                             for _ in os.listdir(os.path.join(root_path, "condition", "overall"))
-        #                         ],
-        #                         examples_per_page=4,
-        #                         inputs=cloth_image_p2p,
-        #                         label="Condition Overall Examples",
-        #                     )
-        #                     condition_person_exm = gr.Examples(
-        #                         examples=[
-        #                             os.path.join(root_path, "condition", "person", _)
-        #                             for _ in os.listdir(os.path.join(root_path, "condition", "person"))
-        #                         ],
-        #                         examples_per_page=4,
-        #                         inputs=cloth_image_p2p,
-        #                         label="Condition Reference Person Examples",
-        #                     )
-        #                     gr.Markdown(
-        #                         '<span style="color: #808080; font-size: small;">*Condition examples come from the Internet. </span>'
-        #                     )
-        # 
-        #         image_path_p2p.change(
-        #             person_example_fn, inputs=image_path_p2p, outputs=person_image_p2p
-        #         )
-        # 
-        #         submit_p2p.click(
-        #             submit_function_p2p,
-        #             [
-        #                 person_image_p2p,
-        #                 cloth_image_p2p,
-        #                 num_inference_steps_p2p,
-        #                 guidance_scale_p2p,
-        #                 seed_p2p],
-        #             result_image_p2p,
-        #         )
+        with gr.Tab("Mask-free & SD1.5"):
+            with gr.Row():
+                with gr.Column(scale=1, min_width=350):
+                    with gr.Row():
+                        image_path_p2p = gr.Video(
+                            type="filepath",
+                            visible=True,
+                        )
+                        person_image_p2p = gr.ImageEditor(
+                            interactive=True, label="Person Image", type="filepath"
+                        )
+
+                    with gr.Row():
+                        with gr.Column(scale=1, min_width=230):
+                            cloth_image_p2p = gr.Image(
+                                interactive=True, label="Condition Image", type="filepath"
+                            )
+
+                    submit_p2p = gr.Button("Submit")
+                    gr.Markdown(
+                        '<center><span style="color: #FF0000">!!! Click only Once, Wait for Delay !!!</span></center>'
+                    )
+
+                    gr.Markdown(
+                        '<span style="color: #808080; font-size: small;">Advanced options can adjust details:<br>1. `Inference Step` may enhance details;<br>2. `CFG` is highly correlated with saturation;<br>3. `Random seed` may improve pseudo-shadow.</span>'
+                    )
+                    with gr.Accordion("Advanced Options", open=False):
+                        num_inference_steps_p2p = gr.Slider(
+                            label="Inference Step", minimum=10, maximum=100, step=5, value=50
+                        )
+                        # Guidence Scale
+                        guidance_scale_p2p = gr.Slider(
+                            label="CFG Strenth", minimum=0.0, maximum=7.5, step=0.5, value=2.5
+                        )
+                        # Random Seed
+                        seed_p2p = gr.Slider(
+                            label="Seed", minimum=-1, maximum=10000, step=1, value=42
+                        )
+                        # show_type = gr.Radio(
+                        #     label="Show Type",
+                        #     choices=["result only", "input & result", "input & mask & result"],
+                        #     value="input & mask & result",
+                        # )
+
+                with gr.Column(scale=2, min_width=500):
+                    #result_image_p2p = gr.Image(interactive=False, label="Result")
+                    gall_output = gr.Gallery(label="Processed Frames")
+
+
+                image_path_p2p.change(
+                    person_example_fn, inputs=image_path_p2p, outputs=person_image_p2p
+                )
+
+                submit_p2p.click(
+                    submit_function_p2p,
+                    [
+                        person_image_p2p,
+                        cloth_image_p2p,
+                        num_inference_steps_p2p,
+                        guidance_scale_p2p,
+                        seed_p2p],
+                    gall_output,
+                )
+
 
     demo.queue().launch(share=True, show_error=True)