invoke-ai/InvokeAI · error · ValueError

LoRA '{lora_key}' is for {stored_config.base.value if stored

Error message

LoRA '{lora_key}' is for {stored_config.base.value if stored_config.base else 'unknown'} models, not Krea-2 models. Ensure you are using a Krea-2 compatible LoRA.

What it means

After fetching the stored model config, invoke() validates that both the caller-supplied lora.base and the stored config are BaseModelType.Krea2 and the config type is ModelType.LoRA. A mismatch (LoRA trained for SDXL/Flux/other architectures, or the stored model is not actually a LoRA) raises this ValueError explaining the LoRA is not Krea-2 compatible.

Source

Thrown at invokeai/app/invocations/krea2_lora_loader.py:69

        default=None,
        title="Qwen3-VL Encoder",
        description=FieldDescriptions.qwen3_vl_encoder,
        input=Input.Connection,
    )

    def invoke(self, context: InvocationContext) -> Krea2LoRALoaderOutput:
        lora_key = self.lora.key

        if not context.models.exists(lora_key):
            raise ValueError(f"Unknown lora: {lora_key}!")

        stored_config = context.models.get_config(lora_key)
        if (
            self.lora.base is not BaseModelType.Krea2
            or stored_config.base is not BaseModelType.Krea2
            or stored_config.type is not ModelType.LoRA
        ):
            raise ValueError(
                f"LoRA '{lora_key}' is for {stored_config.base.value if stored_config.base else 'unknown'} models, "
                "not Krea-2 models. Ensure you are using a Krea-2 compatible LoRA."
            )

        output = Krea2LoRALoaderOutput()

        if self.transformer is not None:
            output.transformer = self.transformer.model_copy(deep=True)
        if self.qwen3_vl_encoder is not None:
            output.qwen3_vl_encoder = self.qwen3_vl_encoder.model_copy(deep=True)

        transformer_lora = (
            next((item for item in output.transformer.loras if item.lora.key == lora_key), None)
            if output.transformer is not None
            else None
        )
        encoder_lora = (
            next((item for item in output.qwen3_vl_encoder.loras if item.lora.key == lora_key), None)

View on GitHub (pinned to 0b6a024f2f)

Solutions

1. Use a LoRA trained for Krea-2 (base must be Krea2) or find a Krea-2 compatible equivalent.
2. Re-import/re-scan the model in the Model Manager so its base and type metadata are detected correctly.
3. Remove the incompatible LoRA node from the workflow or re-point it to a Krea2 model.
4. If the file is genuinely Krea2 but misclassified, fix the model's config (base/type) in the model manager record.

Example fix

// before
loader.lora = ModelIdentifierField(key="abc123")  # SDXL LoRA
// after
loader.lora = ModelIdentifierField(key="def456")  # Krea2 LoRA (base=Krea2, type=LoRA)

from invokeai.backend.model_manager.config import BaseModelType, ModelType
key = loader.lora.key
if loader.lora.base is not BaseModelType.Krea2:
    raise ValueError(f"{key} is not tagged Krea2")
cfg = context.models.get_config(key)
if cfg.base is not BaseModelType.Krea2 or cfg.type is not ModelType.LoRA:
    raise ValueError(f"{key} is {cfg.base.value}/{cfg.type.value}, not a Krea2 LoRA")

def is_krea2_lora(stored_config) -> bool:
    return (
        stored_config.base is BaseModelType.Krea2
        and stored_config.type is ModelType.LoRA
    )

try:
    output = loader.invoke(context)
except ValueError as e:
    if "not Krea-2 models" in str(e):
        raise UserInputError("Choose a Krea-2 trained LoRA; this file targets a different architecture") from e
    raise

When it happens

Trigger: invoke() where self.lora.base != BaseModelType.Krea2, or stored_config.base != BaseModelType.Krea2, or stored_config.type != ModelType.LoRA.

Common situations: Attaching an SDXL or Flux LoRA to a Krea-2 pipeline; a model folder misclassified during import so its base/type metadata is wrong; using an old workflow whose LoRA metadata predates Krea-2 support.

Related errors

• LoRA '{lora.lora.key}' is for {stored_config.base.value if s
• LoRA '{lora.lora.key}' is for {lora.lora.base.value if lora.
• LoRA '{lora.lora.key}' is for {lora.lora.base.value if lora.
• LoRA '{lora.lora.key}' is for {lora.lora.base.value if lora.
• Unknown lora: {lora_key}!

AI-assisted analysis of invoke-ai/InvokeAI@0b6a024f2f (2026-08-29). Data as JSON: /api/errors/7ef6b6635e441b25. Report an issue: GitHub.