calesthio/OpenMontage · error · ValueError

Unsupported MiniMax image model

Error message

Unsupported MiniMax image model '{model}'.

What it means

Raised by MiniMaxImage._build_payload when the 'model' input is not in the module's MODELS allowlist (the default is DEFAULT_MODEL when omitted). The tool only accepts the MiniMax image model ids it was built and tested against, so unknown ids fail fast before any API call.

Solutions

1. Check the tool's get_info()/MODELS list for supported ids and use one of those
2. Update the OpenMontage tool to a version whose MODELS includes the new id
3. If the new model is API-compatible, add its id to MODELS locally and re-verify

Example fix

# before
inputs = {"model": "image-02-live", "prompt": "..."}
# after
inputs = {"model": "image-01", "prompt": "..."}  # an id present in MODELS

from tools.graphics.minimax_image import MODELS
model = inputs.get("model", "image-01")
if model not in MODELS:
    raise ValueError(f"pick one of {sorted(MODELS)}")

def is_supported_minimax_model(model: Any) -> bool:
    return isinstance(model, str) and model in MODELS

When it happens

Trigger: Passing model='image-01-2025' style strings from memory, or a newly released MiniMax model id that the tool version predates; also typos and case mismatch ('Image-01' vs 'image-01').

Common situations: MiniMax releases a new image model and the pinned tool version doesn't know it; copying a model id from a different provider's tool or from newer API docs.

Related errors

• MiniMax image generation requires 'prompt'.
• MiniMax image prompt must not exceed 1500 characters.
• MiniMax image width and height must be set together.
• model must be a non-empty Ark Model/Endpoint ID
• Unsupported Atlas video model id

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/a6beedee22b9843f. Report an issue: GitHub.

Appendix: source

Thrown at tools/graphics/minimax_image.py:176

        return f"MiniMax API error {status_code}: {status_msg}"

    @staticmethod
    def _output_paths(output_path: str | None, count: int) -> list[Path]:
        path = Path(output_path or "minimax_image.png")
        if not path.suffix:
            path = path.with_suffix(".png")
        if count == 1:
            return [path]
        return [
            path.with_name(f"{path.stem}_{index}{path.suffix}")
            for index in range(1, count + 1)
        ]

    @staticmethod
    def _build_payload(inputs: dict[str, Any]) -> dict[str, Any]:
        model = inputs.get("model", DEFAULT_MODEL)
        if model not in MODELS:
            raise ValueError(f"Unsupported MiniMax image model '{model}'.")

        prompt = inputs.get("prompt")
        if not isinstance(prompt, str) or not prompt:
            raise ValueError("MiniMax image generation requires 'prompt'.")
        if len(prompt) > 1500:
            raise ValueError("MiniMax image prompt must not exceed 1500 characters.")

        width = inputs.get("width")
        height = inputs.get("height")
        if (width is None) != (height is None):
            raise ValueError("MiniMax image width and height must be set together.")

        payload: dict[str, Any] = {
            "model": model,
            "prompt": prompt,
            "response_format": inputs.get("response_format", "url"),
            "n": inputs.get("n", 1),
            "prompt_optimizer": inputs.get("prompt_optimizer", False),

View on GitHub (pinned to 95e1c3d0ab)