Function fetch_image

vision_process.py:84–126

(ele: dict[str, str | Image.Image], size_factor: int = IMAGE_FACTOR)

def fetch_image(ele: dict[str, str | Image.Image], size_factor: int = IMAGE_FACTOR) -> Image.Image:
    if "image" in ele:
        image = ele["image"]
    else:
        image = ele["image_url"]
    image_obj = None
    if isinstance(image, Image.Image):
        image_obj = image
    elif image.startswith("http://") or image.startswith("https://"):
        image_obj = Image.open(requests.get(image, stream=True).raw)
    elif image.startswith("file://"):
        image_obj = Image.open(image[7:])
    elif image.startswith("data:image"):
        if "base64," in image:
            _, base64_data = image.split("base64,", 1)
            data = base64.b64decode(base64_data)
            image_obj = Image.open(BytesIO(data))
    else:
        image_obj = Image.open(image)
    if image_obj is None:
        raise ValueError(f"Unrecognized image input, support local path, http url, base64 and PIL.Image, got {image}")
    image = image_obj.convert("RGB")
    ## resize
    if "resized_height" in ele and "resized_width" in ele:
        resized_height, resized_width = smart_resize(
            ele["resized_height"],
            ele["resized_width"],
            factor=size_factor,
        )
    else:
        width, height = image.size
        min_pixels = ele.get("min_pixels", MIN_PIXELS)
        max_pixels = ele.get("max_pixels", MAX_PIXELS)
        resized_height, resized_width = smart_resize(
            height,
            width,
            factor=size_factor,
            min_pixels=min_pixels,
            max_pixels=max_pixels,
        )
    image = image.resize((resized_width, resized_height))

    return image


def smart_nframes(