Upload app.py with huggingface_hub

app.py

@@ -396,15 +396,42 @@ def preprocess_image(input: Image.Image, histogram_normalize: bool = False) -> I
     return output
 
 
-def preprocess_images(images: List[Tuple[Image.Image, str]]) -> List[Image.Image]:
+def apply_histogram_normalization(img: Image.Image) -> Image.Image:
+    """Apply histogram normalization to a preprocessed RGB image (black background)."""
+    arr = np.array(img).astype(np.float32) / 255
+    fg_mask = arr.sum(axis=2) > 0.05
+    if not fg_mask.any():
+        return img
+    for c in range(3):
+        ch = arr[:, :, 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)
+                arr[:, :, c] = np.where(fg_mask, ch_norm, 0)
+    return Image.fromarray((arr * 255).astype(np.uint8))
+
+
+def preprocess_images(images: List[Tuple[Image.Image, str]]) -> Tuple[List[Image.Image], List[Image.Image]]:
     """
     Preprocess a list of input images for multi-image conditioning.
     Uses parallel processing for faster background removal.
+    Returns (gallery_images, base_images_for_state).
     """
     images = [image[0] for image in images]
     with ThreadPoolExecutor(max_workers=min(4, len(images))) as executor:
         processed_images = list(executor.map(preprocess_image, images))
-    return processed_images
+    return processed_images, processed_images
+
+
+def toggle_normalize(base_images: list, histogram_normalize: bool) -> List[Image.Image]:
+    """Toggle histogram normalization on stored base images."""
+    if not base_images:
+        return []
+    if histogram_normalize:
+        return [apply_histogram_normalization(img) for img in base_images]
+    return list(base_images)
 
 
 def pack_state(latents: Tuple[SparseTensor, SparseTensor, int]) -> dict:
@@ -447,10 +474,10 @@ def prepare_multi_example() -> List[str]:
     return examples
 
 
-def load_multi_example(image) -> List[Image.Image]:
-    """Load all views for a multi-image case by matching the input image."""
+def load_multi_example(image) -> Tuple[List[Image.Image], List[Image.Image]]:
+    """Load all views for a multi-image case, preprocess, and store base images."""
     if image is None:
-        return []
+        return [], []
 
     # Convert to PIL Image if needed
     if isinstance(image, np.ndarray):
@@ -463,6 +490,7 @@ def load_multi_example(image) -> List[Image.Image]:
     example_dir = "assets/example_multi_image"
     case_names = sorted(set([f.rsplit('_', 1)[0] for f in os.listdir(example_dir) if f.endswith('.png')]))
 
+    raw_images = None
     for case_name in case_names:
         first_img_path = f'{example_dir}/{case_name}_1.png'
         if os.path.exists(first_img_path):
@@ -471,18 +499,18 @@ def load_multi_example(image) -> List[Image.Image]:
 
             # Compare images (check if same shape and content)
             if input_rgb.shape == first_rgb.shape and np.array_equal(input_rgb, first_rgb):
-                # Found match, load all views (without preprocessing - will be done on Generate)
-                images = []
+                raw_images = []
                 for i in range(1, 7):
                     img_path = f'{example_dir}/{case_name}_{i}.png'
                     if os.path.exists(img_path):
-                        img = Image.open(img_path).convert('RGBA')
-                        images.append(img)
-                if images:
-                    return images
+                        raw_images.append(Image.open(img_path).convert('RGBA'))
+                break
 
-    # No match found, return the single image
-    return [image.convert('RGBA') if image.mode != 'RGBA' else image]
+    if not raw_images:
+        raw_images = [image.convert('RGBA') if image.mode != 'RGBA' else image]
+
+    processed = [preprocess_image(img) for img in raw_images]
+    return processed, processed
 
 
 def split_image(image: Image.Image) -> List[Image.Image]:
@@ -519,16 +547,14 @@ 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:
     if not multiimages:
         raise gr.Error("Please upload images or select an example first.")
 
-    # Preprocess images (background removal, cropping, etc.)
-    images = [image[0] for image in multiimages]
-    processed_images = [preprocess_image(img, histogram_normalize=histogram_normalize) for img in images]
+    # Use gallery images directly (already preprocessed with optional normalization)
+    processed_images = [image[0] for image in multiimages]
 
     # Debug: save preprocessed images and log stats
     for i, img in enumerate(processed_images):
@@ -773,13 +799,14 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="orange", neutral_hue="slate"))
                 examples=prepare_multi_example(),
                 inputs=[example_image],
                 fn=load_multi_example,
-                outputs=[multiimage_prompt],
+                outputs=[multiimage_prompt, preprocessed_state],
                 run_on_click=True,
                 cache_examples=False,
                 examples_per_page=50,
             )
 
     output_buf = gr.State()
+    preprocessed_state = gr.State([])
 
 
     # Handlers
@@ -788,6 +815,16 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="orange", neutral_hue="slate"))
     multiimage_prompt.upload(
         preprocess_images,
         inputs=[multiimage_prompt],
+        outputs=[multiimage_prompt, preprocessed_state],
+    ).then(
+        toggle_normalize,
+        inputs=[preprocessed_state, histogram_normalize],
+        outputs=[multiimage_prompt],
+    )
+
+    histogram_normalize.change(
+        toggle_normalize,
+        inputs=[preprocessed_state, histogram_normalize],
         outputs=[multiimage_prompt],
     )
 
@@ -802,7 +839,7 @@ 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, histogram_normalize
+            multiimage_prompt, multiimage_algo, tex_multiimage_algo
         ],
         outputs=[output_buf, preview_output],
     )