invoke-ai/InvokeAI · error · ValueError

No VAE source provided. Single-file / GGUF transformers requ

Error message

No VAE source provided. Single-file / GGUF transformers require a separate VAE. Options:
  1. Set 'VAE' to a standalone FLUX.2 VAE model
  2. Set 'Mistral Source' to a Diffusers FLUX.2 [dev] model to extract the VAE from

What it means

The FLUX.2 [dev] model loader throws this when a single-file or GGUF transformer is selected but no VAE source is configured. Single-file/GGUF checkpoints do not bundle a VAE, so InvokeAI requires either a standalone FLUX.2 VAE model or a Diffusers FLUX.2 [dev] pipeline from which the VAE can be extracted. The invoke() method raises ValueError as an input-validation gate before any model loading.

Source

Thrown at invokeai/app/invocations/flux2_dev_model_loader.py:139

            raise ValueError(
                f"FLUX.2 [dev] loader requires a FLUX.2 [dev] transformer, "
                f"but the selected model is variant '{variant.value}'. "
                "Use the FLUX.2 Klein loader for Klein variants."
            )

        transformer = self.model.model_copy(update={"submodel_type": SubModelType.Transformer})
        main_is_diffusers = main_config.format == ModelFormat.Diffusers

        # Resolve VAE.
        if self.vae_model is not None:
            vae = self.vae_model.model_copy(update={"submodel_type": SubModelType.VAE})
        elif main_is_diffusers:
            vae = self.model.model_copy(update={"submodel_type": SubModelType.VAE})
        elif self.mistral_source_model is not None:
            self._validate_diffusers_format(context, self.mistral_source_model, "Mistral Source")
            vae = self.mistral_source_model.model_copy(update={"submodel_type": SubModelType.VAE})
        else:
            raise ValueError(
                "No VAE source provided. Single-file / GGUF transformers require a separate VAE. "
                "Options:\n"
                "  1. Set 'VAE' to a standalone FLUX.2 VAE model\n"
                "  2. Set 'Mistral Source' to a Diffusers FLUX.2 [dev] model to extract the VAE from"
            )

        # Resolve Mistral encoder.
        if self.mistral_encoder_model is not None:
            tokenizer = self.mistral_encoder_model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
            text_encoder = self.mistral_encoder_model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
        elif main_is_diffusers:
            tokenizer = self.model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
            text_encoder = self.model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
        elif self.mistral_source_model is not None:
            self._validate_encoder_source(context, self.mistral_source_model, "Mistral Source")
            tokenizer = self.mistral_source_model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
            text_encoder = self.mistral_source_model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
        else:

View on GitHub (pinned to 0b6a024f2f)

Solutions

1. Connect a standalone FLUX.2 VAE model to the loader's 'VAE' input.
2. Connect a Diffusers FLUX.2 [dev] model to the 'Mistral Source' input so the VAE can be extracted from it.

Example fix

// before (workflow graph)
loader = Flux2DevModelLoader(model=gguf_transformer)  # VAE, Mistral Source unconnected
// after
loader = Flux2DevModelLoader(model=gguf_transformer, vae=flux2_vae_model)

# before invoking the loader
if not vae_input and not mistral_source_input:
    raise ValueError("Connect a standalone FLUX.2 VAE or a Diffusers FLUX.2 [dev] 'Mistral Source' before running the loader")

def has_vae_source(loader) -> bool:
    return loader.vae is not None or loader.mistral_source_model is not None

try:
    output = loader.invoke(context)
except ValueError as e:
    if "No VAE source provided" in str(e):
        loader.vae = standalone_flux2_vae
        output = loader.invoke(context)
    else:
        raise

When it happens

Trigger: Invoking the FLUX.2 [dev] model loader where the main model is not a Diffusers pipeline (main_is_diffusers is False), self.vae is unset, and self.mistral_source_model is None.

Common situations: User selects a GGUF or single-file FLUX.2 transformer in the loader node but leaves both the 'VAE' input and the 'Mistral Source' input unconnected in the workflow graph.

Related errors

• No Mistral encoder source provided. Single-file / GGUF trans
• FLUX.2 [dev] loader requires a FLUX.2 [dev] transformer, but
• The {model_name} model must be a Diffusers format model. The
• The {model_name} model must be a FLUX.2 [dev] pipeline, but
• Expected PreTrainedModel for text encoder, got {type(text_en

AI-assisted analysis of invoke-ai/InvokeAI@0b6a024f2f (2026-08-29). Data as JSON: /api/errors/0e9eb79c84610591. Report an issue: GitHub.