Comfy-Org/ComfyUI · error · ValueError

At least one reference image or video or asset is required.

Error message

At least one reference image or video or asset is required.

What it means

The Seedance 2 reference-based generation node requires at least one visual reference: a reference image, reference video, or their asset equivalents. The only exception is Seedance 2.5 (dreamina-seedance-2-5-260628) with audio references. When nothing is connected and the exception does not apply, the node fails fast before any upload or API call.

Source

Thrown at comfy_api_nodes/nodes_bytedance.py:2748

        watermark: bool,
    ) -> IO.NodeOutput:
        validate_string(model["prompt"], strip_whitespace=True, min_length=1)

        reference_images = model.get("reference_images", {})
        reference_videos = model.get("reference_videos", {})
        reference_audios = model.get("reference_audios", {})
        reference_assets = model.get("reference_assets", {})

        reference_image_assets, reference_video_assets, reference_audio_assets = await _resolve_reference_assets(
            cls, list(reference_assets.values())
        )

        model_id = SEEDANCE_MODELS[model["model"]]
        limits = seedance2_reference_limits(model_id)

        if not reference_images and not reference_videos and not reference_image_assets and not reference_video_assets:
            if model_id != "dreamina-seedance-2-5-260628" or not (reference_audios or reference_audio_assets):
                raise ValueError("At least one reference image or video or asset is required.")

        total_images = len(reference_images) + len(reference_image_assets)
        if total_images > limits["max_images"]:
            raise ValueError(
                f"Too many reference images: {total_images} "
                f"(images={len(reference_images)}, image assets={len(reference_image_assets)}). "
                f"Maximum is {limits['max_images']}."
            )
        total_videos = len(reference_videos) + len(reference_video_assets)
        if total_videos > limits["max_videos"]:
            raise ValueError(
                f"Too many reference videos: {total_videos} "
                f"(videos={len(reference_videos)}, video assets={len(reference_video_assets)}). "
                f"Maximum is {limits['max_videos']}."
            )
        total_audios = len(reference_audios) + len(reference_audio_assets)
        if total_audios > limits["max_audios"]:
            raise ValueError(

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Connect at least one reference image or video (or its asset id) to the node.
2. Use the plain text-to-video Seedance node if you want no references.
3. On Seedance 2.5 only: reference audios alone are acceptable if that is the intended mode.

has_visual = bool(reference_images or reference_videos or reference_image_assets or reference_video_assets)
if not has_visual and not (is_seedance_25 and (reference_audios or reference_audio_assets)):
    raise ValueError("connect at least one visual reference")

When it happens

Trigger: Calling the reference-mode node with all reference_images, reference_videos, and reference_assets empty, and either a non-2.5 model or 2.5 with no reference audios either.

Common situations: Using the reference node for text-to-video instead of the t2v node; forgetting to wire references when switching models; iterating on a workflow where the reference branch was deleted.

Related errors

• Either first_frame or first_frame_asset_id is required.
• Provide only one of first_frame or first_frame_asset_id, not
• Provide only one of last_frame or last_frame_asset_id, not b
• Asset {aid} is not an Image asset.
• Too many reference images: {total_images} (images={len(refer

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/5dc7db511be4fc3c. Report an issue: GitHub.