invoke-ai/InvokeAI · error · ValueError

The Component Source model must resolve to a Wan main model.

Error message

The Component Source model must resolve to a Wan main model.

What it means

_validate_component_source_format checks that the 'Component Source' model config has base Wan and type Main before it can be mined for submodels (VAE, tokenizer, text encoder). If it resolves to any other type or base, invoke() (or _validate_component_source_vae) raises this ValueError.

Source

Thrown at invokeai/app/invocations/wan_model_loader.py:318

            transformer=WanTransformerField(
                transformer=transformer,
                transformer_low_noise=transformer_low_noise,
                boundary_ratio=boundary_ratio,
            ),
            wan_t5_encoder=WanT5EncoderField(tokenizer=tokenizer, text_encoder=text_encoder),
            vae=VAEField(vae=vae),
        )

    @staticmethod
    def _validate_main_config(config: object, label: str) -> None:
        if getattr(config, "base", None) != BaseModelType.Wan or getattr(config, "type", None) != ModelType.Main:
            raise ValueError(f"The {label} model must resolve to a Wan main model.")

    @staticmethod
    def _validate_component_source_format(context: InvocationContext, model: ModelIdentifierField) -> None:
        source_config = context.models.get_config(model)
        if source_config.base != BaseModelType.Wan or source_config.type != ModelType.Main:
            raise ValueError("The Component Source model must resolve to a Wan main model.")
        if source_config.format != ModelFormat.Diffusers:
            raise ValueError(
                f"The Component Source model must be in Diffusers format. "
                f"The selected model '{source_config.name}' is in {source_config.format.value} format."
            )

    @staticmethod
    def _validate_component_source_vae(
        context: InvocationContext, model: ModelIdentifierField, main_variant: WanVariantType
    ) -> None:
        WanModelLoaderInvocation._validate_component_source_format(context, model)
        source_config = context.models.get_config(model)
        source_variant = getattr(source_config, "variant", None)
        main_is_ti2v = main_variant == WanVariantType.TI2V_5B
        source_is_ti2v = source_variant == WanVariantType.TI2V_5B
        if main_is_ti2v != source_is_ti2v:
            raise ValueError(
                "The Component Source VAE is incompatible with the selected transformer. "

View on GitHub (pinned to 0b6a024f2f)

Solutions

1. Set 'Component Source' to a Wan Main model (base=Wan, type=Main)
2. Check the model's base/type in the Model Manager and fix metadata if wrong
3. Remove Component Source if not needed and supply standalone VAE/T5 overrides instead

Example fix

// before
component_source=ModelIdentifierField(key='wan-standalone-vae', submodel_type=SubModelType.VAE)
// after
component_source=ModelIdentifierField(key='wan-main-diffusers', submodel_type=SubModelType.Transformer)

cfg = context.models.get_config(invocation.component_source)
if cfg.base != BaseModelType.Wan or cfg.type != ModelType.Main:
    raise ValueError('component_source must be a Wan Main model')

def is_wan_main_source(field, ctx) -> bool:
    cfg = ctx.models.get_config(field)
    return cfg.base == BaseModelType.Wan and cfg.type == ModelType.Main

try:
    output = invocation.invoke(context)
except ValueError as e:
    if 'Component Source model must resolve to a Wan main model' in str(e):
        invocation.component_source = select_wan_main_diffusers_model()

When it happens

Trigger: invoke() or _validate_component_source_vae() called with component_source pointing at a non-Main model (e.g. a standalone VAE or T5 encoder) or a model from another base family.

Common situations: Dropping a component model (VAE/encoder) into the Component Source field by mistake; selecting a Flux or SDXL model as component source; stale workflow referencing a deleted/re-typed model key.

Related errors

• The {label} model must resolve to a Wan main model.
• Unsupported main model format for Wan: {main_format.value}.
• The Wan T5 Encoder must resolve to a standalone Wan T5 encod
• The VAE must resolve to a standalone Wan VAE model.
• FLUX.2 [dev] loader requires a FLUX.2 [dev] transformer, but

AI-assisted analysis of invoke-ai/InvokeAI@0b6a024f2f (2026-08-29). Data as JSON: /api/errors/eb10a1b487d9d678. Report an issue: GitHub.