Upload app.py with huggingface_hub

app.py

@@ -341,7 +341,7 @@ def remove_background(input: Image.Image) -> Image.Image:
         return output
 
 
-def preprocess_image(input: Image.Image) -> Image.Image:
+def preprocess_image(input: Image.Image, histogram_normalize: bool = False) -> Image.Image:
     """
     Preprocess the input image.
     """
@@ -380,19 +380,17 @@ def preprocess_image(input: Image.Image) -> Image.Image:
     alpha = output[:, :, 3:4]
     rgb = rgb * alpha  # premultiply alpha
 
-    # Histogram normalization on foreground pixels only
-    fg_mask = (alpha[:, :, 0] > 0.05)
-    if fg_mask.any():
-        for c in range(3):
-            ch = rgb[:, :, c]
-            fg_vals = ch[fg_mask]
-            if fg_vals.max() > fg_vals.min():
-                # Stretch foreground channel to use full [0, 1] range
-                lo, hi = np.percentile(fg_vals, [1, 99])
-                if hi > lo:
-                    ch_norm = np.clip((ch - lo) / (hi - lo), 0, 1)
-                    # Only apply to foreground pixels
-                    rgb[:, :, c] = np.where(fg_mask, ch_norm, 0)
+    if histogram_normalize:
+        fg_mask = (alpha[:, :, 0] > 0.05)
+        if fg_mask.any():
+            for c in range(3):
+                ch = rgb[:, :, c]
+                fg_vals = ch[fg_mask]
+                if fg_vals.max() > fg_vals.min():
+                    lo, hi = np.percentile(fg_vals, [1, 99])
+                    if hi > lo:
+                        ch_norm = np.clip((ch - lo) / (hi - lo), 0, 1)
+                        rgb[:, :, c] = np.where(fg_mask, ch_norm, 0)
 
     output = Image.fromarray((rgb * 255).astype(np.uint8))
     return output
@@ -521,6 +519,7 @@ def image_to_3d(
     multiimages: List[Tuple[Image.Image, str]],
     multiimage_algo: Literal["multidiffusion", "stochastic"],
     tex_multiimage_algo: Literal["multidiffusion", "stochastic"],
+    histogram_normalize: bool,
     req: gr.Request,
     progress=gr.Progress(track_tqdm=True),
 ) -> str:
@@ -529,7 +528,7 @@ def image_to_3d(
 
     # Preprocess images (background removal, cropping, etc.)
     images = [image[0] for image in multiimages]
-    processed_images = [preprocess_image(img) for img in images]
+    processed_images = [preprocess_image(img, histogram_normalize=histogram_normalize) for img in images]
 
     # Debug: save preprocessed images and log stats
     for i, img in enumerate(processed_images):
@@ -758,6 +757,7 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="orange", neutral_hue="slate"))
                     tex_slat_rescale_t = gr.Slider(1.0, 6.0, label="Rescale T", value=3.0, step=0.1)
                 multiimage_algo = gr.Radio(["stochastic", "multidiffusion"], label="Structure Algorithm", value="stochastic")
                 tex_multiimage_algo = gr.Radio(["stochastic", "multidiffusion"], label="Texture Algorithm", value="stochastic")
+                histogram_normalize = gr.Checkbox(label="Histogram Normalize", value=False)
 
         with gr.Column(scale=10):
             with gr.Row():
@@ -802,7 +802,7 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="orange", neutral_hue="slate"))
             ss_guidance_strength, ss_guidance_rescale, ss_sampling_steps, ss_rescale_t,
             shape_slat_guidance_strength, shape_slat_guidance_rescale, shape_slat_sampling_steps, shape_slat_rescale_t,
             tex_slat_guidance_strength, tex_slat_guidance_rescale, tex_slat_sampling_steps, tex_slat_rescale_t,
-            multiimage_prompt, multiimage_algo, tex_multiimage_algo
+            multiimage_prompt, multiimage_algo, tex_multiimage_algo, histogram_normalize
         ],
         outputs=[output_buf, preview_output],
     )