bug fixes

app.py

@@ -108,6 +108,26 @@ def gen_image(input_image, seed, scale, step):
     return Image.fromarray(np_imgs), Image.fromarray(np_xyzs), glb_path#, obj_path
 
 
+def process_and_generate(input_image, background_choice, foreground_ratio, backgroud_color, seed, scale, step):
+    """Process the input image and generate the 3D model in a single function"""
+    if input_image is None:
+        raise gr.Error("No image uploaded!")
+    
+    # Preprocess the image
+    processed = preprocess_image(input_image, background_choice, foreground_ratio, backgroud_color)
+    
+    # Generate the 3D model
+    pipeline.set_seed(seed)
+    rt_dict = pipeline(processed, scale=scale, step=step)
+    stage1_images = rt_dict["stage1_images"]
+    stage2_images = rt_dict["stage2_images"]
+    np_imgs = np.concatenate(stage1_images, 1)
+    np_xyzs = np.concatenate(stage2_images, 1)
+
+    glb_path = generate3d(model, np_imgs, np_xyzs, args.device)
+    return Image.fromarray(np_imgs), Image.fromarray(np_xyzs), glb_path
+
+# Model initialization code
 parser = argparse.ArgumentParser()
 parser.add_argument(
     "--stage1_config",
@@ -159,6 +179,7 @@ _DESCRIPTION = '''
 * If you find the output unsatisfying, try using different seeds:)
 '''
 
+# Gradio interface
 with gr.Blocks() as demo:
     gr.Markdown("# CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model")
     gr.Markdown(_DESCRIPTION)
@@ -233,22 +254,3 @@ with gr.Blocks() as demo:
     )
     
     demo.queue().launch()
-
-def process_and_generate(input_image, background_choice, foreground_ratio, backgroud_color, seed, scale, step):
-    """Process the input image and generate the 3D model in a single function"""
-    if input_image is None:
-        raise gr.Error("No image uploaded!")
-    
-    # Preprocess the image
-    processed = preprocess_image(input_image, background_choice, foreground_ratio, backgroud_color)
-    
-    # Generate the 3D model
-    pipeline.set_seed(seed)
-    rt_dict = pipeline(processed, scale=scale, step=step)
-    stage1_images = rt_dict["stage1_images"]
-    stage2_images = rt_dict["stage2_images"]
-    np_imgs = np.concatenate(stage1_images, 1)
-    np_xyzs = np.concatenate(stage2_images, 1)
-
-    glb_path = generate3d(model, np_imgs, np_xyzs, args.device)
-    return Image.fromarray(np_imgs), Image.fromarray(np_xyzs), glb_path

requirements.txt

@@ -8,7 +8,7 @@ opencv-contrib-python-headless==4.9.0.80
 opencv-python-headless==4.9.0.80
 xformers
 omegaconf
-gradio==3.16.0
+gradio==4.44.1
 rembg
 git+https://github.com/NVlabs/nvdiffrast
 pygltflib