WanImageProcessor

this repo contains the default image preprocessing code for wan 2.2 5B I2V pipeline

this will load an image from URL, resize and center crop it

image_processor = ModularPipeline.from_pretrained("YiYiXu/WanImageProcessor", trust_remote_code=True)
image = image_processor(
    image="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG",
    max_area=1280*704, output="processed_image")

it does this:

# copied from https://github.com/Wan-Video/Wan2.2/blob/388807310646ed5f318a99f8e8d9ad28c5b65373/wan/utils/utils.py#L136
def best_output_size(w, h, dw, dh, expected_area):
    # float output size
    ratio = w / h
    ow = (expected_area * ratio)**0.5
    oh = expected_area / ow

    # process width first
    ow1 = int(ow // dw * dw)
    oh1 = int(expected_area / ow1 // dh * dh)
    assert ow1 % dw == 0 and oh1 % dh == 0 and ow1 * oh1 <= expected_area
    ratio1 = ow1 / oh1

    # process height first
    oh2 = int(oh // dh * dh)
    ow2 = int(expected_area / oh2 // dw * dw)
    assert oh2 % dh == 0 and ow2 % dw == 0 and ow2 * oh2 <= expected_area
    ratio2 = ow2 / oh2

    # compare ratios
    if max(ratio / ratio1, ratio1 / ratio) < max(ratio / ratio2,
                                                 ratio2 / ratio):
        return ow1, oh1
    else:
        return ow2, oh2

from diffusers.utils import load_image

image = load_image(block_state.image).convert("RGB")
max_area = 1280*704

ih, iw = image.height, image.width
dh, dw = pipe.transformer.config.patch_size[1] * pipe.vae_scale_factor_spatial, pipe.transformer.config.patch_size[2] * pipe.vae_scale_factor_spatial
ow, oh = best_output_size(iw, ih, dw, dh, max_area)

scale = max(ow / iw, oh / ih)
resized_image = image.resize((round(iw * scale), round(ih * scale)), Image.LANCZOS)

# center-crop
x1 = (resized_image.width - ow) // 2
y1 = (resized_image.height - oh) // 2
image = resized_image.crop((x1, y1, x1 + ow, y1 + oh))