lllyasviel/Fooocus · error · FaceWarpException

Not (outer_padding[0] < output_size[0] and outer_padding[1]

Error message

Not (outer_padding[0] < output_size[0] and outer_padding[1] < output_size[1])

What it means

After optional auto-computation of output_size, get_reference_facial_points requires each outer_padding component to be strictly smaller than the corresponding output_size component, otherwise the crop region would be empty or negative. Violating this raises FaceWarpException.

Source

Thrown at extras/facexlib/detection/align_trans.py:84

        return tmp_5pts

    if (inner_padding_factor == 0 and outer_padding == (0, 0)):
        if output_size is None:
            return tmp_5pts
        else:
            raise FaceWarpException('No paddings to do, output_size must be None or {}'.format(tmp_crop_size))

    # check output size
    if not (0 <= inner_padding_factor <= 1.0):
        raise FaceWarpException('Not (0 <= inner_padding_factor <= 1.0)')

    if ((inner_padding_factor > 0 or outer_padding[0] > 0 or outer_padding[1] > 0) and output_size is None):
        output_size = tmp_crop_size * \
            (1 + inner_padding_factor * 2).astype(np.int32)
        output_size += np.array(outer_padding)
    if not (outer_padding[0] < output_size[0] and outer_padding[1] < output_size[1]):
        raise FaceWarpException('Not (outer_padding[0] < output_size[0] and outer_padding[1] < output_size[1])')

    # 1) pad the inner region according inner_padding_factor
    if inner_padding_factor > 0:
        size_diff = tmp_crop_size * inner_padding_factor * 2
        tmp_5pts += size_diff / 2
        tmp_crop_size += np.round(size_diff).astype(np.int32)

    # 2) resize the padded inner region
    size_bf_outer_pad = np.array(output_size) - np.array(outer_padding) * 2

    if size_bf_outer_pad[0] * tmp_crop_size[1] != size_bf_outer_pad[1] * tmp_crop_size[0]:
        raise FaceWarpException('Must have (output_size - outer_padding)'
                                '= some_scale * (crop_size * (1.0 + inner_padding_factor)')

    scale_factor = size_bf_outer_pad[0].astype(np.float32) / tmp_crop_size[0]
    tmp_5pts = tmp_5pts * scale_factor
    #    size_diff = tmp_crop_size * (scale_factor - min(scale_factor))
    #    tmp_5pts = tmp_5pts + size_diff / 2

View on GitHub (pinned to ae05379cc9)

Solutions

1. Reduce outer_padding so each component is strictly less than the corresponding output_size component
2. Scale padding proportionally when changing crop/output size
3. Or set output_size explicitly large enough: output_size > 2*outer_padding + padded crop

Example fix

// before
get_reference_facial_points((256,256), 0.25, (200,200), False, output_size=(256,256))

// after
get_reference_facial_points((256,256), 0.25, (16,16), False, output_size=(320,320))

assert outer_padding[0] < output_size[0] and outer_padding[1] < output_size[1], \
    'outer_padding must be strictly smaller than output_size'

When it happens

Trigger: Calling with outer_padding=(400,400) and output_size=(512,512) — padding is not less than the size; or a small crop_size with zero inner padding that auto-computes an output_size smaller than the requested outer padding.

Common situations: Scaling alignment parameters from a 512-crop pipeline down to smaller crops (e.g. 256) without scaling the outer padding; typo'd padding values; mixing up (x,y) vs (y,x) conventions leading to oversized padding.

Related errors

• No paddings to do, output_size must be None or {}
• Not (0 <= inner_padding_factor <= 1.0)
• Must have (output_size - outer_padding)= some_scale * (crop_
• reference_pts.shape must be (K,2) or (2,K) and K>2
• facial_pts.shape must be (K,2) or (2,K) and K>2

AI-assisted analysis of lllyasviel/Fooocus@ae05379cc9 (2026-08-15). Data as JSON: /api/errors/27202e20caeda4b4. Report an issue: GitHub.