Create app.py

app.py

@@ -0,0 +1,107 @@
+import gradio as gr
+from transformers import AutoImageProcessor, SegformerForSemanticSegmentation, pipeline
+from PIL import Image, ImageOps, ImageFilter
+import numpy as np
+import torch
+
+# ----- Load models once -----
+seg_model_id = "nvidia/segformer-b0-finetuned-ade-512-512"
+depth_model_id = "depth-anything/Depth-Anything-V2-Base-hf"
+
+seg_processor = AutoImageProcessor.from_pretrained(seg_model_id)
+seg_model = SegformerForSemanticSegmentation.from_pretrained(seg_model_id)
+
+depth_pipe = pipeline(
+    task="depth-estimation",
+    model=depth_model_id,
+    device=0 if torch.cuda.is_available() else -1,
+)
+
+# ----- Gaussian background blur using segmentation -----
+def gaussian_background_blur(img: Image.Image) -> Image.Image:
+    img = ImageOps.fit(img.convert("RGB"), (512, 512), method=Image.BICUBIC)
+
+    inputs = seg_processor(images=img, return_tensors="pt")
+    with torch.no_grad():
+        outputs = seg_model(**inputs)
+
+    logits = outputs.logits
+    upsampled = torch.nn.functional.interpolate(
+        logits, size=(512, 512), mode="bilinear", align_corners=False
+    )
+    seg = upsampled.argmax(dim=1)[0].cpu().numpy()
+
+    id2label = seg_model.config.id2label
+    person_ids = [i for i, label in id2label.items() if "person" in label.lower()]
+    mask = np.isin(seg, person_ids).astype(np.uint8)
+
+    mask_pil = Image.fromarray(mask * 255, mode="L")
+    blurred_bg = img.filter(ImageFilter.GaussianBlur(radius=15))
+    out = Image.composite(img, blurred_bg, mask_pil)
+    return out
+
+# ----- Depth-based lens blur -----
+def depth_lens_blur(img: Image.Image) -> Image.Image:
+    img = ImageOps.fit(img.convert("RGB"), (512, 512), method=Image.BICUBIC)
+
+    depth_output = depth_pipe(img)
+    depth_tensor = depth_output["predicted_depth"]
+    depth_np = depth_tensor.squeeze().cpu().numpy()
+
+    # normalize, then invert so far = more blur, near = sharp
+    d_min, d_max = depth_np.min(), depth_np.max()
+    depth_norm = (depth_np - d_min) / (d_max - d_min + 1e-8)  # [0,1]
+    blur_norm = 1.0 - depth_norm    # near≈1 -> 0 blur, far≈0 -> 1 blur
+
+    max_radius = 15.0
+    num_levels = 6
+    radii = np.linspace(0, max_radius, num_levels)
+    blurred_versions = [
+        img.filter(ImageFilter.GaussianBlur(radius=float(r))) for r in radii
+    ]
+    blurred_np = [np.array(b) for b in blurred_versions]
+
+    level_size = 1.0 / (num_levels - 1)
+    blur_levels = np.floor(blur_norm / level_size).astype(np.int32)
+    blur_levels = np.clip(blur_levels, 0, num_levels - 1)
+
+    H, W = blur_levels.shape
+    out_np = np.zeros((H, W, 3), dtype=np.uint8)
+
+    for lvl in range(num_levels):
+        mask = blur_levels == lvl
+        if not np.any(mask):
+            continue
+        mask_3c = np.repeat(mask[:, :, None], 3, axis=2)
+        out_np[mask_3c] = blurred_np[lvl][mask_3c]
+
+    return Image.fromarray(out_np)
+
+# ----- Gradio UI -----
+def apply_effect(img, mode):
+    if img is None:
+        return None
+    if mode == "Gaussian background blur":
+        return gaussian_background_blur(img)
+    elif mode == "Depth-based lens blur":
+        return depth_lens_blur(img)
+    else:
+        return img
+
+demo = gr.Interface(
+    fn=apply_effect,
+    inputs=[
+        gr.Image(type="pil", label="Upload an image"),
+        gr.Radio(
+            ["Gaussian background blur", "Depth-based lens blur"],
+            value="Gaussian background blur",
+            label="Effect",
+        ),
+    ],
+    outputs=gr.Image(label="Output"),
+    title="Gaussian & Depth-based Lens Blur Demo",
+    description="Upload a selfie or scene and choose Gaussian background blur or depth-based lens blur.",
+)
+
+if __name__ == "__main__":
+    demo.launch()