Update app.py

app.py

@@ -7,32 +7,8 @@ from gradio_imageslider import ImageSlider
 from huggingface_hub import hf_hub_download
 from controlnet_union import ControlNetModel_Union
 from pipeline_fill_sd_xl import StableDiffusionXLFillPipeline
-from gradio_image_prompter import ImagePrompter
 from PIL import Image, ImageDraw
 import numpy as np
-# from sam2.sam2_image_predictor import SAM2ImagePredictor
-# from sam2_mask import create_sam2_tab
-import subprocess
-import os
-
-subprocess.run("rm -rf /data-nvme/zerogpu-offload/*", env={}, shell=True)
-HF_TOKEN = os.environ["HF_TOKEN"]
-
-# class SAM2PredictorSingleton:
-#     _instance = None
-
-#     def __new__(cls):
-#         if cls._instance is None:
-#             cls._instance = super(SAM2PredictorSingleton, cls).__new__(cls)
-#             cls._instance._initialize_predictor()
-#         return cls._instance
-
-#     def _initialize_predictor(self):
-#         MODEL = "facebook/sam2-hiera-large"
-#         DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-#         self.predictor = SAM2ImagePredictor.from_pretrained(MODEL, device=DEVICE)
-
-PREDICTOR = None
 
 MODELS = {
     "RealVisXL V5.0 Lightning": "SG161222/RealVisXL_V5.0_Lightning",
@@ -81,59 +57,6 @@ def load_default_pipeline():
     ).to("cuda")
     return gr.update(value="Default pipeline loaded!")
 
-# @spaces.GPU()
-# def predict_masks(prompts):
-
-#     DEVICE = torch.device("cuda")
-#     SAM_MODEL = "facebook/sam2.1-hiera-large"
-#     # if PREDICTOR is None:
-#     #     PREDICTOR = SAM2ImagePredictor.from_pretrained(SAM_MODEL, device=DEVICE)
-#     # else:
-#     #     PREDICTOR = PREDICTOR
-#     PREDICTOR = SAM2ImagePredictor.from_pretrained(SAM_MODEL, device=DEVICE)
-
-#     """Predict a single mask from the image based on selected points."""
-#     image = np.array(prompts["image"])  # Convert the image to a numpy array
-#     points = prompts["points"]  # Get the points from prompts
-
-#     if not points:
-#         return image  # Return the original image if no points are selected
-
-#     # Debugging: Print the structure of points
-#     print(f"Points structure: {points}")
-
-#     # Ensure points is a list of lists with at least two elements
-#     if isinstance(points, list) and all(isinstance(point, list) and len(point) >= 2 for point in points):
-#         input_points = [[point[0], point[1]] for point in points]
-#     else:
-#         return image  # Return the original image if points structure is unexpected
-
-#     input_labels = [1] * len(input_points)
-
-#     with torch.inference_mode():
-#         PREDICTOR.set_image(image)
-#         masks, _, _ = PREDICTOR.predict(
-#             point_coords=input_points, point_labels=input_labels, multimask_output=False
-#         )
-
-#     # Prepare the overlay image
-#     red_mask = np.zeros_like(image)
-#     if masks and len(masks) > 0:
-#         red_mask[:, :, 0] = masks[0].astype(np.uint8) * 255  # Apply the red channel
-#         red_mask = PILImage.fromarray(red_mask)
-#         original_image = PILImage.fromarray(image)
-#         blended_image = PILImage.blend(original_image, red_mask, alpha=0.5)
-#         return np.array(blended_image)
-#     else:
-#         return image
-
-# def update_mask(prompts):
-#     """Update the mask based on the prompts."""
-#     image = prompts["image"]
-#     points = prompts["points"]
-#     return predict_masks(image, points)
-
-
 @spaces.GPU(duration=12)
 def fill_image(prompt, image, model_selection, paste_back):
     print(f"Received image: {image}")
@@ -193,8 +116,6 @@ def prepare_image_and_mask(image, width, height, overlap_percentage, resize_opti
         resize_percentage = 100
     elif resize_option == "80%":
         resize_percentage = 80
-    elif resize_option == "67%":
-        resize_percentage = 67
     elif resize_option == "50%":
         resize_percentage = 50
     elif resize_option == "33%":
@@ -387,7 +308,6 @@ def clear_cache():
     torch.cuda.empty_cache()
     return gr.update(value="Cache cleared!")
 
-
 css = """
 .nulgradio-container {
     width: 86vw !important;
@@ -399,9 +319,6 @@ css = """
 div#component-17 {
     height: auto !important;
 }
-div#component-46{
-    height: 100% !important;
-}
 """
 
 title = """<h1 align="center">Diffusers Image Outpaint</h1>
@@ -414,7 +331,6 @@ title = """<h1 align="center">Diffusers Image Outpaint</h1>
     </p>
 </div>
 """
-sam_block = gr.load(name="spaces/LPX55/SAM2_1-Image-Predictor-Masking-Tool-CPU")
 
 with gr.Blocks(css=css, fill_height=True) as demo:
     gr.Markdown("# Diffusers Inpaint and Outpaint")
@@ -556,6 +472,15 @@ with gr.Blocks(css=css, fill_height=True) as demo:
                                     )
                                 with gr.Column():
                                     preview_button = gr.Button("Preview alignment and mask")
+                        gr.Examples(
+                            examples=[
+                                ["./examples/example_1.webp", 1280, 720, "Middle"],
+                                ["./examples/example_2.jpg", 1440, 810, "Left"],
+                                ["./examples/example_3.jpg", 1024, 1024, "Top"],
+                                ["./examples/example_3.jpg", 1024, 1024, "Bottom"],
+                            ],
+                            inputs=[input_image_outpaint, width_slider, height_slider, alignment_dropdown],
+                        )
                     with gr.Column():
                         result_outpaint = ImageSlider(
                             interactive=False,
@@ -564,34 +489,6 @@ with gr.Blocks(css=css, fill_height=True) as demo:
                         use_as_input_button_outpaint = gr.Button("Use as Input Image", visible=False)
                         history_gallery = gr.Gallery(label="History", columns=6, object_fit="contain", interactive=False)
                         preview_image = gr.Image(label="Preview")
-        # with gr.TabItem("SAM2 Masking"):
-        #     input_image, points_map, output_result_mask = create_sam2_tab()
-        # with gr.TabItem("SAM2 Mask"):
-        #     gr.Markdown("# Object Segmentation with SAM2")
-        #     gr.Markdown(
-        #         """
-        #         This application utilizes **Segment Anything V2 (SAM2)** to allow you to upload an image and interactively generate a segmentation mask based on multiple points you select on the image.
-        #         """
-        #     )
-        #     with gr.Row():
-        #         with gr.Column():
-        #             image_input = gr.State()
-        #             # Input: ImagePrompter for uploaded image
-        #             upload_image_input = ImagePrompter(show_label=False)
-        #         with gr.Column():
-        #             image_output = gr.Image(label="Segmented Image", type="pil", height=400)
-        #         with gr.Row():
-        #         # Button to trigger the prediction
-        #             predict_button = gr.Button("Predict Mask")
-                
-        #         # Define the action triggered by the predict button
-        #         predict_button.click(
-        #             fn=predict_masks,
-        #             inputs=[upload_image_input],
-        #             outputs=[image_output],
-        #             show_progress=True,
-        #         )
-        
         with gr.TabItem("Misc"):
             with gr.Column():
                 clear_cache_button = gr.Button("Clear CUDA Cache")
@@ -608,11 +505,6 @@ with gr.Blocks(css=css, fill_height=True) as demo:
                     inputs=None,
                     outputs=load_default_message,
                 )
-
-    # upload_image_input.change(
-    #     fn=lambda img: img, inputs=upload_image_input, outputs=image_input
-    # )
-    
     target_ratio.change(
         fn=preload_presets,
         inputs=[target_ratio, width_slider, height_slider],