Release: v0.33.2

Author: Wauplin

src/huggingface_hub/__init__.py

@@ -46,7 +46,7 @@
 from typing import TYPE_CHECKING
 
 
-__version__ = "0.33.1"
+__version__ = "0.33.2"
 
 # Alphabetical order of definitions is ensured in tests
 # WARNING: any comment added in this dictionary definition will be lost when

src/huggingface_hub/inference/_client.py

@@ -947,8 +947,8 @@ def document_question_answering(
         Answer questions on document images.
 
         Args:
-            image (`Union[str, Path, bytes, BinaryIO]`):
-                The input image for the context. It can be raw bytes, an image file, or a URL to an online image.
+            image (`Union[str, Path, bytes, BinaryIO, PIL.Image.Image]`):
+                The input image for the context. It can be raw bytes, an image file, a URL to an online image, or a PIL Image.
             question (`str`):
                 Question to be answered.
             model (`str`, *optional*):
@@ -1156,8 +1156,8 @@ def image_classification(
         Perform image classification on the given image using the specified model.
 
         Args:
-            image (`Union[str, Path, bytes, BinaryIO]`):
-                The image to classify. It can be raw bytes, an image file, or a URL to an online image.
+            image (`Union[str, Path, bytes, BinaryIO, PIL.Image.Image]`):
+                The image to classify. It can be raw bytes, an image file, a URL to an online image, or a PIL Image.
             model (`str`, *optional*):
                 The model to use for image classification. Can be a model ID hosted on the Hugging Face Hub or a URL to a
                 deployed Inference Endpoint. If not provided, the default recommended model for image classification will be used.
@@ -1214,8 +1214,8 @@ def image_segmentation(
         </Tip>
 
         Args:
-            image (`Union[str, Path, bytes, BinaryIO]`):
-                The image to segment. It can be raw bytes, an image file, or a URL to an online image.
+            image (`Union[str, Path, bytes, BinaryIO, PIL.Image.Image]`):
+                The image to segment. It can be raw bytes, an image file, a URL to an online image, or a PIL Image.
             model (`str`, *optional*):
                 The model to use for image segmentation. Can be a model ID hosted on the Hugging Face Hub or a URL to a
                 deployed Inference Endpoint. If not provided, the default recommended model for image segmentation will be used.
@@ -1286,8 +1286,8 @@ def image_to_image(
         </Tip>
 
         Args:
-            image (`Union[str, Path, bytes, BinaryIO]`):
-                The input image for translation. It can be raw bytes, an image file, or a URL to an online image.
+            image (`Union[str, Path, bytes, BinaryIO, PIL.Image.Image]`):
+                The input image for translation. It can be raw bytes, an image file, a URL to an online image, or a PIL Image.
             prompt (`str`, *optional*):
                 The text prompt to guide the image generation.
             negative_prompt (`str`, *optional*):
@@ -1348,8 +1348,8 @@ def image_to_text(self, image: ContentT, *, model: Optional[str] = None) -> Imag
         (OCR), Pix2Struct, etc). Please have a look to the model card to learn more about a model's specificities.
 
         Args:
-            image (`Union[str, Path, bytes, BinaryIO]`):
-                The input image to caption. It can be raw bytes, an image file, or a URL to an online image..
+            image (`Union[str, Path, bytes, BinaryIO, PIL.Image.Image]`):
+                The input image to caption. It can be raw bytes, an image file, a URL to an online image, or a PIL Image.
             model (`str`, *optional*):
                 The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed
                 Inference Endpoint. This parameter overrides the model defined at the instance level. Defaults to None.
@@ -1399,8 +1399,8 @@ def object_detection(
         </Tip>
 
         Args:
-            image (`Union[str, Path, bytes, BinaryIO]`):
-                The image to detect objects on. It can be raw bytes, an image file, or a URL to an online image.
+            image (`Union[str, Path, bytes, BinaryIO, PIL.Image.Image]`):
+                The image to detect objects on. It can be raw bytes, an image file, a URL to an online image, or a PIL Image.
             model (`str`, *optional*):
                 The model to use for object detection. Can be a model ID hosted on the Hugging Face Hub or a URL to a
                 deployed Inference Endpoint. If not provided, the default recommended model for object detection (DETR) will be used.
@@ -2974,8 +2974,8 @@ def visual_question_answering(
         Answering open-ended questions based on an image.
 
         Args:
-            image (`Union[str, Path, bytes, BinaryIO]`):
-                The input image for the context. It can be raw bytes, an image file, or a URL to an online image.
+            image (`Union[str, Path, bytes, BinaryIO, PIL.Image.Image]`):
+                The input image for the context. It can be raw bytes, an image file, a URL to an online image, or a PIL Image.
             question (`str`):
                 Question to be answered.
             model (`str`, *optional*):
@@ -3141,8 +3141,8 @@ def zero_shot_image_classification(
         Provide input image and text labels to predict text labels for the image.
 
         Args:
-            image (`Union[str, Path, bytes, BinaryIO]`):
-                The input image to caption. It can be raw bytes, an image file, or a URL to an online image.
+            image (`Union[str, Path, bytes, BinaryIO, PIL.Image.Image]`):
+                The input image to caption. It can be raw bytes, an image file, a URL to an online image, or a PIL Image.
             candidate_labels (`List[str]`):
                 The candidate labels for this image
             labels (`List[str]`, *optional*):

src/huggingface_hub/inference/_common.py

@@ -61,7 +61,7 @@
 UrlT = str
 PathT = Union[str, Path]
 BinaryT = Union[bytes, BinaryIO]
-ContentT = Union[BinaryT, PathT, UrlT]
+ContentT = Union[BinaryT, PathT, UrlT, "Image"]
 
 # Use to set a Accept: image/png header
 TASKS_EXPECTING_IMAGES = {"text-to-image", "image-to-image"}
@@ -164,7 +164,6 @@ def _open_as_binary(content: Optional[ContentT]) -> Generator[Optional[BinaryT],
 
     Do nothing if `content` is None,
 
-    TODO: handle a PIL.Image as input
     TODO: handle base64 as input
     """
     # If content is a string => must be either a URL or a path
@@ -185,6 +184,12 @@ def _open_as_binary(content: Optional[ContentT]) -> Generator[Optional[BinaryT],
         logger.debug(f"Opening content from {content}")
         with content.open("rb") as f:
             yield f
+    elif hasattr(content, "save"):  # PIL Image
+        logger.debug("Converting PIL Image to bytes")
+        buffer = io.BytesIO()
+        content.save(buffer, format="PNG")
+        buffer.seek(0)
+        yield buffer
     else:
         # Otherwise: already a file-like object or None
         yield content