Comfy-Org/ComfyUI · error · ValueError

SeedVR2PostProcessing: LAB color correction requires at leas

Error message

SeedVR2PostProcessing: LAB color correction requires at least one frame.

What it means

The LAB color-transfer loop iterates over decoded_flat.shape[0]; if that is 0 (no frames at all) the loop never runs, result stays None, and this error is raised. It is effectively an empty-input guard for the per-frame lab_color_transfer path.

Source

Thrown at comfy_extras/nodes_seedvr.py:276

        return output.to(device=output_device)

    @staticmethod
    def _lab_color_transfer_on_vae_device(decoded_flat, reference_flat, output_device):
        color_device = comfy.model_management.vae_device()
        result = None
        for start in range(decoded_flat.shape[0]):
            decoded_frame = decoded_flat[start:start + 1].to(device=color_device).clone()
            reference_frame = reference_flat[start:start + 1].to(device=color_device).clone()
            output = lab_color_transfer(decoded_frame, reference_frame).to(device=output_device)
            if result is None:
                result = torch.empty(
                    (decoded_flat.shape[0],) + tuple(output.shape[1:]),
                    device=output_device,
                    dtype=output.dtype,
                )
            result[start:start + 1].copy_(output)
        if result is None:
            raise ValueError("SeedVR2PostProcessing: LAB color correction requires at least one frame.")
        return result

    @classmethod
    def _color_transfer_chunked(cls, decoded_flat, reference_flat, output_device, color_correction_method):
        chunk_size = cls._estimate_color_correction_chunk_size(decoded_flat, color_correction_method)
        while True:
            try:
                return cls._run_color_transfer_chunks(
                    decoded_flat, reference_flat, output_device, color_correction_method, chunk_size,
                )
            except Exception as e:
                comfy.model_management.raise_non_oom(e)
                if chunk_size <= 1:
                    raise RuntimeError(
                        "SeedVR2PostProcessing: color correction OOM at one frame; "
                        f"color_correction_method={color_correction_method}, shape={tuple(decoded_flat.shape)}."
                    ) from e
                chunk_size = max(1, chunk_size // SEEDVR2_OOM_BACKOFF_DIVISOR)

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Ensure the decoded image batch has at least one frame before calling the node (tensor.shape[0] >= 1).
2. Fix the upstream frame selection that produced an empty batch.
3. Skip color correction entirely for empty inputs instead of invoking the node.

Example fix

# before
frames = [f for f in frames if f.mean() > 0]  # may become []
out = postprocess(torch.stack(frames))

# after
if not frames:
    raise ValueError('no frames to process')
out = postprocess(torch.stack(frames))

if decoded_flat.shape[0] < 1:
    raise ValueError('cannot run LAB color correction on 0 frames')

def has_at_least_one_frame(t) -> bool:
    return t.dim() >= 1 and t.shape[0] >= 1

When it happens

Trigger: A decoded tensor with a zero-length frame/batch dimension reaching the LAB color correction branch — e.g. an empty image list converted to a 0-frame tensor upstream.

Common situations: Empty batch from a filtered/empty image set; an upstream node emitting 0 frames (empty video range); a placeholder tensor created with torch.empty(0,3,H,W).

Related errors

• SeedVR2PostProcessing: color correction requires at least on
• No images provided to create_image_parts; at least one image
• Cannot create grid from empty image list
• SplatToFile3D: gaussian is empty
• Expression cannot be empty.

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/507f96e5af6f48ef. Report an issue: GitHub.