Comfy-Org/ComfyUI · error · ValueError

The maximum number of reference images is 7.

Error message

The maximum number of reference images is 7.

What it means

Raised by OmniProImageToVideoNode.execute when the reference_images batch exceeds 7 images. This node (first-frame driven image-to-video) allows up to 7 omni reference images; the count check happens before upload via get_number_of_images.

Source

Thrown at comfy_api_nodes/nodes_kling.py:1103

                sb_prompt = storyboards[f"storyboard_{i}_prompt"]
                sb_duration = storyboards[f"storyboard_{i}_duration"]
                validate_string(sb_prompt, field_name=f"storyboard_{i}_prompt", min_length=1, max_length=512)
                multi_prompt_list.append(
                    MultiPromptEntry(
                        index=i,
                        prompt=sb_prompt,
                        duration=str(sb_duration),
                    )
                )
            total_storyboard_duration = sum(int(e.duration) for e in multi_prompt_list)
            if total_storyboard_duration != duration:
                raise ValueError(
                    f"Total storyboard duration ({total_storyboard_duration}s) "
                    f"must equal the global duration ({duration}s)."
                )

        if get_number_of_images(reference_images) > 7:
            raise ValueError("The maximum number of reference images is 7.")
        for i in reference_images:
            validate_image_dimensions(i, min_width=300, min_height=300)
            validate_image_aspect_ratio(i, (1, 2.5), (2.5, 1))
        image_list: list[OmniParamImage] = []
        for i in await upload_images_to_comfyapi(cls, reference_images, wait_label="Uploading reference image"):
            image_list.append(OmniParamImage(image_url=i))
        if resolution == "4k":
            mode = "4k"
        elif resolution == "1080p":
            mode = "pro"
        else:
            mode = "std"
        response = await sync_op(
            cls,
            ApiEndpoint(path="/proxy/kling/v1/videos/omni-video", method="POST"),
            response_model=TaskStatusResponse,
            data=OmniProReferences2VideoRequest(
                model_name=model_name,

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Slice the reference batch to at most 7 images
2. Curate the reference set down to the most informative frames
3. Check for stray/duplicate frames in the source folder feeding the batch

Example fix

# before
reference_images = folder_batch.images  # 12 images

# after
reference_images = folder_batch.images[:7]  # <= 7

def reference_count_ok_image2video(reference_images) -> bool:
    return reference_images is None or get_number_of_images(reference_images) <= 7

When it happens

Trigger: Connecting a batch of 8+ images to reference_images on the OmniPro image-to-video node.

Common situations: A folder loader or batch-concat node emits more frames than expected (hidden extra files, growing folder), pushing the count past 7.

Related errors

• The maximum number of reference images allowed is 6.
• The maximum number of reference images allowed with a video
• The maximum number of reference images is 10.
• Reference video {i} is too short: {dur:.1f}s. Minimum durati
• Total reference video duration is {total_video_duration:.1f}

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/6f35aa2cab630769. Report an issue: GitHub.