Comfy-Org/ComfyUI · error · ValueError

SeedVR2TemporalChunk: temporal_overlap must be >= 0; got {te

Error message

SeedVR2TemporalChunk: temporal_overlap must be >= 0; got {temporal_overlap}.

What it means

SeedVR2TemporalChunk.execute validates the temporal_overlap input (an Int with min=0 in the UI, but force_input means an API or wire can supply anything). A negative value would make the chunk step computation nonsensical, so it fails fast with this message.

Source

Thrown at comfy_extras/nodes_seedvr.py:468

                              tooltip="The effective latent-frame overlap between adjacent chunks, for Merge SeedVR2 Latents."),
            ],
        )

    @classmethod
    def execute(cls, latent, temporal_overlap, chunking_mode) -> io.NodeOutput:
        samples = latent["samples"]
        if samples.ndim != 5:
            raise ValueError(
                f"SeedVR2TemporalChunk: expected a 5-D video latent (B, C, T, H, W); "
                f"got shape {tuple(samples.shape)}."
            )
        if samples.shape[1] != SEEDVR2_LATENT_CHANNELS:
            raise ValueError(
                f"SeedVR2TemporalChunk: expected {SEEDVR2_LATENT_CHANNELS} latent channels; "
                f"got shape {tuple(samples.shape)}."
            )
        if temporal_overlap < 0:
            raise ValueError(
                f"SeedVR2TemporalChunk: temporal_overlap must be >= 0; got {temporal_overlap}."
            )
        mode = chunking_mode["chunking_mode"]
        if mode not in ("auto", "manual"):
            raise ValueError(
                f"SeedVR2TemporalChunk: chunking_mode must be 'auto' or 'manual'; "
                f"got {mode!r}."
            )
        t_latent = samples.shape[2]
        t_pixel = 4 * (t_latent - 1) + 1

        if mode == "auto":
            free_gb = comfy.model_management.get_free_memory(
                comfy.model_management.get_torch_device()) / (1024 ** 3)
            mpx_per_frame = (samples.shape[0] * samples.shape[3] * samples.shape[4]) * (BYTEDANCE_VAE_SPATIAL_DOWNSAMPLE ** 2) / 1e6
            budget_gb = free_gb - SEEDVR2_CHUNK_RESERVED_GIB - SEEDVR2_CHUNK_SIGMA_K * SEEDVR2_CHUNK_SIGMA_GIB
            chunk_latent_max = max(1, int(budget_gb / (SEEDVR2_CHUNK_GIB_PER_MPX_FRAME * mpx_per_frame)))
            frames_per_chunk = min(4 * (chunk_latent_max - 1) + 1, t_pixel)

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Clamp the value before queueing: temporal_overlap = max(0, temporal_overlap).
2. Keep temporal_overlap between 0 and the chunk's latent length minus 1; typical values are 0-2.
3. When computing overlap from other parameters, validate the result is non-negative before building the prompt.

Example fix

# before
overlap = desired - safety_margin  # can go negative
prompt['inputs']['temporal_overlap'] = overlap

# after
prompt['inputs']['temporal_overlap'] = max(0, overlap)

temporal_overlap = max(0, int(temporal_overlap))

def is_valid_overlap(v) -> bool:
    return isinstance(v, int) and v >= 0

When it happens

Trigger: Queueing a prompt via the API with temporal_overlap=-1, or wiring an integer source node that computes a negative value into the temporal_overlap input.

Common situations: Programmatic prompt construction that passes a computed overlap like min_overlap - 1 without clamping; workflows authored outside the UI which do not enforce the widget's min=0.

Related errors

• SeedVR2TemporalChunk: frames_per_chunk must be a 4n+1 pixel-
• SeedVR2TemporalMerge: temporal_overlap must be >= 0; got {te
• SeedVR2TemporalChunk: expected a 5-D video latent (B, C, T,
• SeedVR2TemporalChunk: expected {SEEDVR2_LATENT_CHANNELS} lat
• SeedVR2TemporalChunk: chunking_mode must be 'auto' or 'manua

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/29e04a470c8d9110. Report an issue: GitHub.