Comfy-Org/ComfyUI · error · ValueError

Too many reference videos: {total_videos} (videos={len(refer

Error message

Too many reference videos: {total_videos} (videos={len(reference_videos)}, video assets={len(reference_video_assets)}). Maximum is {limits['max_videos']}.

What it means

Client-side cap on reference videos: the number of direct reference_videos plus resolved video assets must not exceed limits["max_videos"] (10 for Seedance 2.5). Videos are heavy inputs both for upload time and provider-side processing, so the node rejects over-quota inputs before uploading anything.

Source

Thrown at comfy_api_nodes/nodes_bytedance.py:2759

        )

        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(
                f"Too many reference audios: {total_audios} "
                f"(audios={len(reference_audios)}, audio assets={len(reference_audio_assets)}). "
                f"Maximum is {limits['max_audios']}."
            )

        for key in reference_images:
            reference_images[key] = _prepare_seedance_image(reference_images[key])

        has_video_input = total_videos > 0

        if model.get("auto_downscale") and reference_videos:

View on GitHub (pinned to 1c6d8d45b3)

Solutions

Trim the reference video list to the stated maximum.
Concatenate or pre-select the most relevant clips and pass fewer videos.
Use image references for style/identity and keep video references for motion only.

Defensive patterns

Strategy: validation

Validate before calling

total = len(reference_videos) + len(reference_video_assets)
assert total <= seedance2_reference_limits(model_id)["max_videos"]

Prevention

Keep video references to the few clips that actually carry the motion you need.
Re-check the cap when switching models.

When it happens

Trigger: Connecting more reference video inputs than the model's max_videos, or combining reference_videos and reference_assets video ids above the cap.

Common situations: Multi-shot reference workflows with many clips; combining old uploaded video assets with newly connected clips.

Related errors

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/05fa6217c5bec308. Report an issue: GitHub.