Comfy-Org/ComfyUI · error · ValueError

The {model_id} model supports at most {max_images} input ima

Error message

The {model_id} model supports at most {max_images} input image{'s' if max_images > 1 else ''}; {n_images} are connected.

What it means

Per-model input image cap in the dict-driven Grok image edit node. _GROK_IMAGE_EDIT_MAX_IMAGES maps grok-imagine-image-pro to 1 and the other grok image models to 3 (fallback 3). The summed image count across all connected tensors is compared against the selected model's cap, and exceeding it reports both the cap and the connected count.

Source

Thrown at comfy_api_nodes/nodes_grok.py:586

        cls,
        prompt: str,
        model: dict,
        seed: int,
    ) -> IO.NodeOutput:
        validate_string(prompt, strip_whitespace=True, min_length=1)
        model_id = model["model"]
        resolution = model["resolution"]
        number_of_images = model["number_of_images"]
        images_dict = model.get("images") or {}
        aspect_ratio = model.get("aspect_ratio", "auto")

        image_tensors: list[Input.Image] = [t for t in images_dict.values() if t is not None]
        n_images = sum(get_number_of_images(t) for t in image_tensors)
        max_images = _GROK_IMAGE_EDIT_MAX_IMAGES.get(model_id, 3)
        if n_images < 1:
            raise ValueError("At least one image is required for editing.")
        if n_images > max_images:
            raise ValueError(
                f"The {model_id} model supports at most {max_images} input "
                f"image{'s' if max_images > 1 else ''}; {n_images} are connected."
            )
        if aspect_ratio != "auto" and model_id in _GROK_IMAGE_EDIT_ASPECT_RATIO_NEEDS_MULTIPLE and n_images == 1:
            raise ValueError(
                "Custom aspect ratio is only allowed when multiple images are connected to the image input."
            )

        flat_tensors: list[torch.Tensor] = []
        for tensor in image_tensors:
            if len(tensor.shape) == 4:
                flat_tensors.extend(tensor[i] for i in range(tensor.shape[0]))
            else:
                flat_tensors.append(tensor)

        response = await sync_op(
            cls,
            ApiEndpoint(path="/proxy/xai/v1/images/edits", method="POST"),

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Trim connected images to the model's cap (1 for pro, 3 for others).
2. Switch to a model whose cap fits your input count.
3. Slice batched tensors so the summed count fits.

Example fix

# before: model_id='grok-imagine-image-pro', 2 images connected
await grok_edit_execute(model={'model': 'grok-imagine-image-pro', 'images': {'a': i1, 'b': i2}, ...}, seed=1)  # raises

# after: keep only the primary reference
await grok_edit_execute(model={'model': 'grok-imagine-image-pro', 'images': {'a': i1}, ...}, seed=1)

CAPS = {"grok-imagine-image-2.0": 3, "grok-imagine-image-pro": 1,
       "grok-imagine-image-quality": 3, "grok-imagine-image": 3}
n = sum(get_number_of_images(t) for t in tensors if t is not None)
assert n <= CAPS.get(model_id, 3), f"{n} images > cap {CAPS.get(model_id, 3)} for {model_id}"

When it happens

Trigger: n_images = sum(get_number_of_images(t)) over connected tensors exceeds _GROK_IMAGE_EDIT_MAX_IMAGES[model_id] — e.g. 2 images with pro (cap 1) or 4 images with grok-imagine-image (cap 3).

Common situations: Changing the model dropdown to pro without trimming inputs; batched tensors whose batch dimension silently multiplies the count; workflows shared between models with different caps.

Related errors

• The pro model supports only 1 input image.
• A maximum of 3 input images is supported.
• Custom aspect ratio is only allowed when multiple images are
• At least one image is required for editing.
• The prompt references @Image{idx}, but only {total_images} r

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/610abdc54089f11d. Report an issue: GitHub.