diff --git a/src/transformers/models/idefics3/image_processing_idefics3.py b/src/transformers/models/idefics3/image_processing_idefics3.py
index bf21f06e8c5..b0677c4708d 100644
--- a/src/transformers/models/idefics3/image_processing_idefics3.py
+++ b/src/transformers/models/idefics3/image_processing_idefics3.py
@@ -581,7 +581,7 @@ class Idefics3ImageProcessor(BaseImageProcessor):
         padded_images_list = [
             [empty_image(pad_size, data_format) for _ in range(max_num_images)] for _ in range(batch_size)
         ]
-        padded_masks = [[np.zeros(pad_size) for _ in range(max_num_images)] for _ in range(batch_size)]
+        padded_masks = [[np.zeros(pad_size, dtype=np.int64) for _ in range(max_num_images)] for _ in range(batch_size)]
 
         for batch_idx in range(batch_size):
             for sample_idx, image in enumerate(images[batch_idx]):
diff --git a/src/transformers/models/smolvlm/image_processing_smolvlm.py b/src/transformers/models/smolvlm/image_processing_smolvlm.py
index 93ed18d1344..abf9353fd4e 100644
--- a/src/transformers/models/smolvlm/image_processing_smolvlm.py
+++ b/src/transformers/models/smolvlm/image_processing_smolvlm.py
@@ -578,7 +578,7 @@ class SmolVLMImageProcessor(BaseImageProcessor):
         padded_images_list = [
             [empty_image(pad_size, data_format) for _ in range(max_num_images)] for _ in range(batch_size)
         ]
-        padded_masks = [[np.zeros(pad_size) for _ in range(max_num_images)] for _ in range(batch_size)]
+        padded_masks = [[np.zeros(pad_size, dtype=np.int64) for _ in range(max_num_images)] for _ in range(batch_size)]
 
         for batch_idx in range(batch_size):
             for sample_idx, image in enumerate(images[batch_idx]):