invoke-ai/InvokeAI · error · ValueError

LoRA '{lora.lora.key}' is for {lora.lora.base.value if lora.

Error message

LoRA '{lora.lora.key}' is for {lora.lora.base.value if lora.lora.base else 'unknown'} models, not Anima models. Ensure you are using an Anima compatible LoRA.

What it means

The loader validates that each LoRA's base model type is BaseModelType.Anima. LoRAs trained for other architectures (SDXL, Flux, SD1.x, etc.) have incompatible weight shapes and target modules, so applying them would corrupt the model. The error names the LoRA's actual base type and asks for an Anima-compatible LoRA.

Source

Thrown at invokeai/app/invocations/anima_lora_loader.py:153

        added_loras: list[str] = []

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

        if self.qwen3_encoder is not None:
            output.qwen3_encoder = self.qwen3_encoder.model_copy(deep=True)

        for lora in loras:
            if lora is None:
                continue
            if lora.lora.key in added_loras:
                continue

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

            if lora.lora.base is not BaseModelType.Anima:
                raise ValueError(
                    f"LoRA '{lora.lora.key}' is for {lora.lora.base.value if lora.lora.base else 'unknown'} models, "
                    "not Anima models. Ensure you are using an Anima compatible LoRA."
                )

            added_loras.append(lora.lora.key)

            if self.transformer is not None and output.transformer is not None:
                output.transformer.loras.append(lora)

            if self.qwen3_encoder is not None and output.qwen3_encoder is not None:
                output.qwen3_encoder.loras.append(lora)

        return output

View on GitHub (pinned to 0b6a024f2f)

Solutions

Replace the LoRA with one explicitly trained for Anima models.
Check the LoRA's base model metadata in the model manager and correct it if mislabeled.
Remove the incompatible LoRA from the workflow before running.

Example fix

// before
lora = LoraSelector(lora=sdxl_lora_key, weight=0.8)  # base=SDXL
// after
lora = LoraSelector(lora=anima_lora_key, weight=0.8)  # base=Anima

Defensive patterns

Strategy: validation

Validate before calling

from invokeai.backend.model_manager.config import BaseModelType
for lora in loras:
    if lora.lora.base is not BaseModelType.Anima:
        print(f"Skip {lora.lora.key}: base={lora.lora.base}")

Type guard

def is_anima_lora(lora) -> bool:
    from invokeai.backend.model_manager.config import BaseModelType
    return lora.lora.base is BaseModelType.Anima

Try / catch

try:
    output = lora_loader.invoke(context)
except ValueError as e:
    if "not Anima models" in str(e):
        swap_to_anima_lora(e)
    else:
        raise

Prevention

Only download LoRAs explicitly labeled for Anima; check base model metadata before use.
Never reuse LoRA selector nodes across pipelines with different base model types.
Verify LoRA metadata after import; a None base type is a red flag.

When it happens

Trigger: Invoking AnimaLoRALoader with any LoRA in self.transformer.loras whose lora.lora.base is not BaseModelType.Anima (None base also triggers the 'unknown' variant).

Common situations: Dragging an SDXL/Flux LoRA from a shared workflow into an Anima pipeline; downloading a LoRA for the wrong architecture from Civitai; a LoRA file with missing/incorrect metadata so its base type resolves to None.

Related errors

AI-assisted analysis of invoke-ai/InvokeAI@0b6a024f2f (2026-08-29). Data as JSON: /api/errors/803d0c57ef54016a. Report an issue: GitHub.