Comfy-Org/ComfyUI · error · ValueError

The current maximum number of supported images is 14.

Error message

The current maximum number of supported images is 14.

What it means

Client-side validation in the Gemini image generation node (single-input variant): the connected image input batch contains more than 14 images, which is the API's current maximum number of reference images for image generation/editing. The count is computed with get_number_of_images, so a batched tensor of N images counts as N. It fails before any network call.

Source

Thrown at comfy_api_nodes/nodes_gemini.py:1125

        model: str,
        seed: int,
        aspect_ratio: str,
        resolution: str,
        response_modalities: str,
        images: Input.Image | None = None,
        files: list[GeminiPart] | None = None,
        system_prompt: str = "",
    ) -> IO.NodeOutput:
        validate_string(prompt, strip_whitespace=True, min_length=1)
        if model == "Nano Banana 2 (Gemini 3.1 Flash Image)":
            model = "gemini-3.1-flash-image"
        elif model == "gemini-3-pro-image-preview":
            model = "gemini-3-pro-image"

        parts: list[GeminiPart] = [GeminiPart(text=prompt)]
        if images is not None:
            if get_number_of_images(images) > 14:
                raise ValueError("The current maximum number of supported images is 14.")
            parts.extend(await create_image_parts(cls, images))
        if files is not None:
            parts.extend(files)

        image_config = GeminiImageConfig(imageSize=resolution)
        if aspect_ratio != "auto":
            image_config.aspectRatio = aspect_ratio

        gemini_system_prompt = None
        if system_prompt:
            gemini_system_prompt = GeminiSystemInstructionContent(parts=[GeminiTextPart(text=system_prompt)], role=None)

        response = await sync_op(
            cls,
            ApiEndpoint(path=f"/proxy/vertexai/gemini/{model}", method="POST"),
            data=GeminiImageGenerateContentRequest(
                contents=[
                    GeminiContent(role=GeminiRole.user, parts=parts),

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Split the input into batches of at most 14 images and run the node multiple times.
2. Trim the source list/tensor to the 14 most relevant images before connecting it.
3. If using a batched tensor, slice it: images[:14].

Example fix

# before
await generate(prompt, images=all_frames)  # all_frames has 20 images -> raises

# after
await generate(prompt, images=all_frames[:14])

from comfy_api_nodes.nodes_gemini import get_number_of_images  # conceptually
n = get_number_of_images(images)
assert n <= 14, f"{n} images connected; Gemini allows at most 14"

When it happens

Trigger: Executing GeminiImageGenerator-style node with an images input where get_number_of_images(images) > 14 — e.g. one batched tensor of 15+ frames or several tensors whose total exceeds 14.

Common situations: Feeding a video frame batch or image grid directly into the reference image input; chaining a load-image-folder node that emits 20 images; iterating workflows where batch size was tuned for a different model's higher limit.

Related errors

• The current maximum number of supported images is {OMNI_MAX_
• The current maximum number of supported videos is {OMNI_MAX_
• Gemini did not generate an image. Try rephrasing your prompt
• The pro model supports only 1 input image.
• A maximum of 3 input images is supported.

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/5643fe7684a6f890. Report an issue: GitHub.