app.py

import gradio as gr
import numpy as np
from PIL import Image, ImageDraw
import torch
from transformers import AutoProcessor, CLIPSegForImageSegmentation

# Load the CLIPSeg model and processor
processor = AutoProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined")

def segment_everything(image):
    inputs = processor(text=["object"], images=[image], padding="max_length", return_tensors="pt")
    with torch.no_grad():
        outputs = model(**inputs)
    preds = outputs.logits.squeeze().sigmoid()
    segmentation = (preds.numpy() * 255).astype(np.uint8)
    return Image.fromarray(segmentation)

def segment_box(image, box):
    x1, y1, x2, y2 = map(int, box)
    mask = Image.new('L', image.size, 0)
    draw = ImageDraw.Draw(mask)
    draw.rectangle([x1, y1, x2, y2], fill=255)
    
    inputs = processor(text=["object in box"], images=[image], mask_pixels=mask, padding="max_length", return_tensors="pt")
    with torch.no_grad():
        outputs = model(**inputs)
    preds = outputs.logits.squeeze().sigmoid()
    segmentation = (preds.numpy() * 255).astype(np.uint8)
    return Image.fromarray(segmentation)

def update_image(image, segmentation, tool):
    if segmentation is None:
        return image
    blended = Image.blend(image.convert('RGBA'), segmentation.convert('RGBA'), 0.5)
    return blended

with gr.Blocks() as demo:
    gr.Markdown("# Segment Anything-like Demo")
    with gr.Row():
        with gr.Column(scale=1):
            input_image = gr.Image(label="Input Image", tool="select")
            with gr.Row():
                everything_btn = gr.Button("Everything")
                box_btn = gr.Button("Box")
        with gr.Column(scale=1):
            output_image = gr.Image(label="Segmentation Result")
    
    everything_btn.click(
        fn=segment_everything,
        inputs=[input_image],
        outputs=[output_image]
    )
    
    box_btn.click(
        fn=segment_box,
        inputs=[input_image, input_image.sel],
        outputs=[output_image]
    )
    
    output_image.change(
        fn=update_image,
        inputs=[input_image, output_image, gr.State("last_tool")],
        outputs=[output_image]
    )

demo.launch()