Create app.py

app.py

@@ -0,0 +1,141 @@
+import spaces
+import gradio as gr
+import torch
+from PIL import Image
+from torchvision import transforms
+from transformers import AutoModelForImageSegmentation
+
+torch.set_float32_matmul_precision("high")
+
+print("Loading BiRefNet...")
+birefnet = AutoModelForImageSegmentation.from_pretrained(
+    "ZhengPeng7/BiRefNet", trust_remote_code=True
+)
+birefnet.to("cuda")
+birefnet.eval()
+birefnet.half()
+print("Model ready.")
+
+IMAGE_SIZE = (1024, 1024)
+
+transform_image = transforms.Compose([
+    transforms.Resize(IMAGE_SIZE),
+    transforms.ToTensor(),
+    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
+])
+
+
+@spaces.GPU(duration=30)
+def cutout_model(image: Image.Image):
+    """Removes the background from the model photo, returns RGBA cutout."""
+    original = image.convert("RGB")
+    input_tensor = transform_image(original).unsqueeze(0).to("cuda").half()
+
+    with torch.no_grad():
+        preds = birefnet(input_tensor)[-1].sigmoid().cpu()
+
+    mask = preds[0].squeeze()
+    mask_pil = transforms.ToPILImage()(mask).resize(original.size)
+
+    cutout = original.copy()
+    cutout.putalpha(mask_pil)
+    return cutout
+
+
+def compose_thumbnail(thumbnail, model_photo, scale, x_pos, y_pos):
+    if thumbnail is None:
+        raise gr.Error("Please upload a thumbnail/background image.")
+    if model_photo is None:
+        raise gr.Error("Please upload a model photo.")
+
+    try:
+        thumbnail = thumbnail.convert("RGBA")
+        cutout = cutout_model(model_photo)
+
+        # Scale the cutout relative to the thumbnail's height
+        thumb_w, thumb_h = thumbnail.size
+        target_h = int(thumb_h * (scale / 100.0))
+        aspect = cutout.width / cutout.height
+        target_w = int(target_h * aspect)
+        cutout_resized = cutout.resize((target_w, target_h), Image.LANCZOS)
+
+        # Position: x_pos/y_pos are percentages of thumbnail width/height,
+        # representing where the CENTER of the cutout should land.
+        center_x = int(thumb_w * (x_pos / 100.0))
+        center_y = int(thumb_h * (y_pos / 100.0))
+        paste_x = center_x - target_w // 2
+        paste_y = center_y - target_h // 2
+
+        result = thumbnail.copy()
+        result.paste(cutout_resized, (paste_x, paste_y), cutout_resized)
+        return result.convert("RGB")
+
+    except Exception as e:
+        import traceback
+        traceback.print_exc()
+        raise gr.Error(f"Compositing failed: {e}")
+
+
+css = """
+#header {
+    text-align: center;
+    padding: 24px 0 8px;
+}
+#header h1 {
+    font-size: 32px;
+    font-weight: 700;
+    background: linear-gradient(135deg, #6366f1, #06b6d4);
+    -webkit-background-clip: text;
+    -webkit-text-fill-color: transparent;
+    margin-bottom: 4px;
+}
+#header p {
+    color: #888;
+    font-size: 14px;
+}
+#run-btn {
+    background: linear-gradient(135deg, #6366f1, #06b6d4) !important;
+    color: white !important;
+    font-weight: 600 !important;
+    border: none !important;
+}
+"""
+
+with gr.Blocks(title="Peace Network Thumbnail Composer", css=css) as demo:
+    gr.HTML(
+        """
+        <div id="header">
+            <h1>🎬 Peace Network Thumbnail Composer</h1>
+            <p>Thumbnail background + model photo daaliye — model automatically fit ho jayega.</p>
+        </div>
+        """
+    )
+
+    with gr.Row():
+        thumb_input = gr.Image(type="pil", label="1. Thumbnail / background")
+        model_input = gr.Image(type="pil", label="2. Model photo")
+
+    with gr.Row():
+        scale_slider = gr.Slider(
+            minimum=10, maximum=100, value=60, step=1,
+            label="Model size (% of thumbnail height)"
+        )
+        x_slider = gr.Slider(
+            minimum=0, maximum=100, value=50, step=1,
+            label="Horizontal position (%)"
+        )
+        y_slider = gr.Slider(
+            minimum=0, maximum=100, value=70, step=1,
+            label="Vertical position (%)"
+        )
+
+    btn = gr.Button("✨ Compose Thumbnail", variant="primary", elem_id="run-btn")
+    output = gr.Image(type="pil", label="Result")
+
+    btn.click(
+        compose_thumbnail,
+        inputs=[thumb_input, model_input, scale_slider, x_slider, y_slider],
+        outputs=output,
+    )
+
+demo.queue().launch()