lllyasviel/Fooocus · error · ValueError

scale {scale} is not supported. Supported scales: 2^n and 3.

Error message

scale {scale} is not supported. Supported scales: 2^n and 3.

What it means

SwinIR.Upsample: the BasicSR-style tail accepts power-of-two scales (repeated 2x PixelShuffle) or scale 3; all other values raise ValueError. SwinIR SR models therefore only exist for 2x/3x/4x/8x.

Source

Thrown at ldm_patched/pfn/architecture/SwinIR.py:758

class Upsample(nn.Sequential):
    """Upsample module.

    Args:
        scale (int): Scale factor. Supported scales: 2^n and 3.
        num_feat (int): Channel number of intermediate features.
    """

    def __init__(self, scale, num_feat):
        m = []
        if (scale & (scale - 1)) == 0:  # scale = 2^n
            for _ in range(int(math.log(scale, 2))):
                m.append(nn.Conv2d(num_feat, 4 * num_feat, 3, 1, 1))
                m.append(nn.PixelShuffle(2))
        elif scale == 3:
            m.append(nn.Conv2d(num_feat, 9 * num_feat, 3, 1, 1))
            m.append(nn.PixelShuffle(3))
        else:
            raise ValueError(
                f"scale {scale} is not supported. " "Supported scales: 2^n and 3."
            )
        super(Upsample, self).__init__(*m)


class UpsampleOneStep(nn.Sequential):
    """UpsampleOneStep module (the difference with Upsample is that it always only has 1conv + 1pixelshuffle)
       Used in lightweight SR to save parameters.

    Args:
        scale (int): Scale factor. Supported scales: 2^n and 3.
        num_feat (int): Channel number of intermediate features.

    """

    def __init__(self, scale, num_feat, num_out_ch, input_resolution=None):
        self.num_feat = num_feat
        self.input_resolution = input_resolution

View on GitHub (pinned to ae05379cc9)

Solutions

  1. Use upscale 2, 4, 8 or 3
  2. Chain 2x + 3x passes for 6x
  3. Validate scale early in config loading

Example fix

# before
m = SwinIR(upscale=6, ...)  # -> ValueError

# after
m = SwinIR(upscale=4, ...)
Defensive patterns

Strategy: validation

Validate before calling

def valid_sr_scale(scale) -> bool:
    return scale == 3 or (isinstance(scale, int) and scale > 1 and (scale & (scale - 1)) == 0)

upscale = int(cfg.get('upscale', 4))
if not valid_sr_scale(upscale):
    cfg['upscale'] = 4  # or raise a config error with context

Type guard

def is_supported_swinir_scale(scale) -> bool:
    return isinstance(scale, int) and (scale == 3 or (scale & (scale - 1)) == 0)

Prevention

When it happens

Trigger: Instantiating SwinIR with upscale outside {2,4,8,...,3}; e.g. porting a config with scale 6, or passing a computed ratio like 5 when registering a custom upscaler.

Common situations: Custom upscaler YAML copied from another arch; scripts deriving upscale from image sizes; typos in scale fields (e.g. 2.5).

Related errors

AI-assisted analysis of lllyasviel/Fooocus@ae05379cc9 (2026-08-15). Data as JSON: /api/errors/7bc75a53d343514e. Report an issue: GitHub.