关于Flux2klein的图像预处理gap

你好，我在diffuser库中观察到，cond image只有在大于目标尺寸1024时才会进行防缩。

condition_images = []
for img in image:
    image_width, image_height = img.size
    if image_width * image_height > 1024 * 1024:
        img = self.image_processor._resize_to_target_area(img, 1024 * 1024)
        image_width, image_height = img.size

    multiple_of = self.vae_scale_factor * 2
    image_width = (image_width // multiple_of) * multiple_of
    image_height = (image_height // multiple_of) * multiple_of
    img = self.image_processor.preprocess(img, height=image_height, width=image_width, resize_mode="crop")
    condition_images.append(img)
    height = height or image_height
    width = width or image_width

但是我在本代码仓库观察到，似乎会强制将cond防缩到1024的size

def calculate_dimensions(self, target_area, ratio):
        import math
        width = math.sqrt(target_area * ratio)
        height = width / ratio
        width = round(width / 32) * 32
        height = round(height / 32) * 32
        return width, height
    
    def crop_and_resize(self, image, target_height, target_width):
        width, height = image.size
        scale = max(target_width / width, target_height / height)
        image = torchvision.transforms.functional.resize(
            image,
            (round(height*scale), round(width*scale)),
            interpolation=torchvision.transforms.InterpolationMode.BILINEAR
        )
        image = torchvision.transforms.functional.center_crop(image, (target_height, target_width))
        return image

    def edit_image_auto_resize(self, edit_image):
        calculated_width, calculated_height = self.calculate_dimensions(1024 * 1024, edit_image.size[0] / edit_image.size[1])
        return self.crop_and_resize(edit_image, calculated_height, calculated_width)

Start by tracing edit_image_auto_resize and its calculate_dimensions and crop_and_resize helpers, then compare their behavior with the condition-image preprocessing shown in the issue. Confirm whether Flux2klein should resize every image to a 1024×1024 target area or only images exceeding it; done means the chosen behavior is implemented consistently and verified against representative image sizes.