calesthio/OpenMontage · error · ValueError

model_name {model_name!r} is not supported for api_family=ge

Error message

model_name {model_name!r} is not supported for api_family=generation

What it means

ValueError raised when building a Kling image-generation request (api_family=generation, the default, targeting /v1/images/generations) with a model_name that is not in the IMAGE_GENERATION_MODELS allowlist. The tool refuses to submit an unknown model rather than letting the API fail opaquely.

Source

Thrown at tools/graphics/kling_official_image.py:259

            artifacts=[str(path) for path in paths],
            cost_usd=self.estimate_cost(inputs),
            duration_seconds=round(time.time() - start, 2),
            model=request["model"],
        )

    def _build_request(self, inputs: dict[str, Any]) -> dict[str, Any]:
        api_family = str(inputs.get("api_family", "generation"))
        if inputs.get("operation") == "omni":
            api_family = "omni"
        if api_family == "omni":
            return self._build_omni_request(inputs)
        return self._build_generation_request(inputs)

    def _build_generation_request(self, inputs: dict[str, Any]) -> dict[str, Any]:
        prompt = self._prompt(inputs)
        model_name = str(inputs.get("model_name") or "kling-v3")
        if model_name not in IMAGE_GENERATION_MODELS:
            raise ValueError(f"model_name {model_name!r} is not supported for api_family=generation")
        payload: dict[str, Any] = {
            "model_name": model_name,
            "prompt": prompt,
            "resolution": inputs.get("resolution", "1k"),
            "n": int(inputs.get("n", 1) or 1),
            "aspect_ratio": inputs.get("aspect_ratio", "16:9"),
        }
        if len(prompt) > 2500:
            raise ValueError("prompt exceeds Kling image generation limit of 2500 characters")
        if inputs.get("negative_prompt"):
            payload["negative_prompt"] = inputs["negative_prompt"]
        image = normalize_image_input(inputs.get("image_url"), inputs.get("image_path"))
        if image:
            payload["image"] = image
        if inputs.get("image_reference"):
            payload["image_reference"] = inputs["image_reference"]
        for key in ("image_fidelity", "human_fidelity"):
            if inputs.get(key) is not None:

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Use a model from IMAGE_GENERATION_MODELS (e.g. kling-v3) for api_family=generation
2. If you want an omni model such as kling-image-o1, set operation='omni' or api_family='omni' instead
3. Check for typos/whitespace in the model_name string
4. If Kling shipped a genuinely new model, update IMAGE_GENERATION_MODELS in kling_official_image.py after verifying API support

Example fix

// before
inputs = {"api_family": "generation", "model_name": "kling-image-o1"}
// after
inputs = {"api_family": "omni", "model_name": "kling-image-o1"}

IMAGE_GENERATION_MODELS = {"kling-v3"}  # mirror the tool's allowlist
model = inputs.get("model_name") or "kling-v3"
assert model in IMAGE_GENERATION_MODELS, f"unsupported generation model: {model}"

When it happens

Trigger: Explicitly passing model_name of an omni-family model (e.g. kling-image-o1) while api_family stays 'generation'; passing a video model name; typo like 'kling-v4' or 'kling-v3 ' (whitespace); passing an empty-ish value is safe (defaults to kling-v3) — only non-member strings raise.

Common situations: Copy-pasting a model name from a different tool or API family; Kling released a new model not yet in the allowlist; mixing up the generation and omni API families.

Related errors

• model_name {model_name!r} is not supported for api_family=om
• prompt exceeds Kling image generation limit of 2500 characte
• image_list items must be objects
• image_list items must include image, image_url, or image_pat
• element_list must be a list of element ids or objects

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/50682a23218f211e. Report an issue: GitHub.