Add Big-LaMa model exported with CoreMLtools

LaMa.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:289f2c611bd3e52805ee3e686e290981d96d3b9674db93fe6bf30962f7e60d87
+size 1166404

LaMa.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae26da8deca02ead81120f1d683b6c38361cd593c5a685e543c4b84726500e1
+size 204086656

LaMa.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "058403EC-D454-47EC-9C08-D1149DC8311C": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "BCCB46DC-D6B9-4B28-8D24-B59CF8160E49": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "058403EC-D454-47EC-9C08-D1149DC8311C"
+}

app.py

@@ -0,0 +1,56 @@
+import gradio as gr
+import coremltools as ct
+import numpy as np
+from PIL import Image
+import io
+
+# Load the model
+coreml_model_file_name = "LaMa.mlpackage"
+loaded_model = ct.models.MLModel(coreml_model_file_name)
+
+def inpaint(input_dict):
+    # Resize input image and mask to 800x800
+    input_image = input_dict["background"].convert("RGB").resize((800, 800), Image.LANCZOS)
+    input_mask = pil_to_binary_mask(input_dict['layers'][0].resize((800, 800), Image.NEAREST))
+
+    # Convert mask to grayscale
+    input_mask = input_mask.convert("L")
+
+    # Run inference
+    prediction = loaded_model.predict({"image": input_image, "mask": input_mask})
+
+    # Access the output
+    output_image = prediction["output"]
+
+    return output_image, input_mask
+
+def pil_to_binary_mask(pil_image, threshold=0):
+    np_image = np.array(pil_image)
+    grayscale_image = Image.fromarray(np_image).convert("L")
+    binary_mask = np.array(grayscale_image) > threshold
+    mask = np.zeros(binary_mask.shape, dtype=np.uint8)
+    for i in range(binary_mask.shape[0]):
+        for j in range(binary_mask.shape[1]):
+            if binary_mask[i,j] == True :
+                mask[i,j] = 1
+    mask = (mask*255).astype(np.uint8)
+    output_mask = Image.fromarray(mask)
+    return output_mask
+
+# Create Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Image Inpainting")
+    gr.Markdown("Upload an image and draw a mask to remove unwanted objects.")
+    
+    with gr.Row():
+        input_image = gr.ImageEditor(type="pil", label='Input image & Mask', interactive=True)
+        output_image = gr.Image(type="pil", label="Output Image")
+    with gr.Column():
+        masked_image = gr.Image(label="Masked image", type="pil")
+
+    inpaint_button = gr.Button("Inpaint")
+    inpaint_button.click(fn=inpaint, inputs=[input_image], outputs=[output_image, masked_image])
+
+# Launch the interface
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+coremltools
+numpy
+pillow