invoke-ai/InvokeAI · error · ValueError

Wan reference condition requires batch size 1; got {conditio

Error message

Wan reference condition requires batch size 1; got {condition.shape[0]}.

What it means

The reference condition must have batch size exactly 1 (shape[0] == 1). Batched conditioning is not supported by this Wan path, so _validate_ref_condition_shape rejects any tensor whose first dimension is greater than 1.

Source

Thrown at invokeai/app/invocations/wan_denoise.py:106

    if variant == WanVariantType.TI2V_5B and (width % 32 or height % 32):
        raise ValueError(
            f"TI2V-5B requires width and height to be multiples of 32 (got {width}x{height}). "
            "Wan 2.2-VAE 16x spatial * transformer patch_size 2 = pixel dims must divide by 32."
        )


def _validate_ref_condition_shape(
    condition: torch.Tensor,
    *,
    channels: int,
    frames: int,
    height: int,
    width: int,
) -> None:
    if condition.ndim != 5:
        raise ValueError(f"Wan reference condition must be a 5D tensor; got shape {tuple(condition.shape)}.")
    if condition.shape[0] != 1:
        raise ValueError(f"Wan reference condition requires batch size 1; got {condition.shape[0]}.")
    if condition.shape[1] != channels:
        raise ValueError(f"Wan reference condition requires {channels} channels; got {condition.shape[1]}.")
    if condition.shape[2] != frames:
        expected = "a single latent frame" if frames == 1 else f"{frames} latent frames"
        raise ValueError(f"Wan reference condition requires {expected}; got {condition.shape[2]}.")
    if condition.shape[3:] != (height, width):
        raise ValueError(
            f"Wan reference condition requires {width}x{height} latent spatial dimensions; "
            f"got {condition.shape[4]}x{condition.shape[3]}."
        )


def _scheduler_path_for_transformer(context: InvocationContext, transformer_field: WanTransformerField) -> Path | None:
    """Return the on-disk ``scheduler/`` directory for the main model, or None."""
    config = context.models.get_config(transformer_field.transformer)
    model_root = context.models.get_absolute_path(config)
    if model_root.is_file():
        return None

View on GitHub (pinned to 0b6a024f2f)

Solutions

Set batch size to 1 for the conditioning path (condition = condition[:1] or don't batch it)
Generate each batch item in a separate invocation instead of batching the ref condition
If multiple reference images are needed, stack along the frames dimension only if the model supports it, otherwise use one ref per run
Check the upstream latents/condition node's batch setting

Example fix

// before
condition = torch.cat([ref1, ref2], dim=0)  # batch 2
// after
condition = ref1.unsqueeze(0)  # batch 1; run a second invocation for ref2

Defensive patterns

Strategy: validation

Validate before calling

if condition.shape[0] != 1:
    condition = condition[:1]  # keep only the first batch item before invoking

Type guard

def is_batch_1(t) -> bool:
    import torch
    return isinstance(t, torch.Tensor) and t.ndim == 5 and t.shape[0] == 1

Try / catch

try:
    result = denoise.invoke(context)
except ValueError as e:
    if "requires batch size 1" in str(e):
        denoise.ref_condition = denoise.ref_condition[:1]
        result = denoise.invoke(context)
    else:
        raise

Prevention

Keep global batch size at 1 when using reference conditioning
Generate batch items via separate invocations, not batched conditions
Never stack multiple reference images along dim 0
Assert condition.shape[0] == 1 in custom scripts before invoking

When it happens

Trigger: Passing a condition tensor produced with batch size 2+ (e.g. batch-generating latents, duplicating the image latent along dim 0, or a upstream node configured with batch_size > 1) into the Wan ref-condition input.

Common situations: Users setting a global batch size > 1 for speed and expecting ref conditioning to follow, batched img2img pipelines feeding a single-video ref input, scripting that stacks multiple reference images along the batch axis.

Related errors

AI-assisted analysis of invoke-ai/InvokeAI@0b6a024f2f (2026-08-29). Data as JSON: /api/errors/ba4b3c4971247273. Report an issue: GitHub.