Comfy-Org/ComfyUI · error · ValueError

kling-video-o1 does not support durations greater than 10 se

Error message

kling-video-o1 does not support durations greater than 10 seconds.

What it means

Image-to-video variant of the o1 duration guard: for kling-video-o1 i2v, duration must be at most 10 seconds (checked as duration > 10, slightly looser than the t2v node's exact 5-or-10 check, though the later per-model branch still enforces 5/10). Any duration above 10 raises before the request.

Source

Thrown at comfy_api_nodes/nodes_kling.py:869

    @classmethod
    async def execute(
        cls,
        model_name: str,
        prompt: str,
        duration: int,
        first_frame: Input.Image,
        end_frame: Input.Image | None = None,
        reference_images: Input.Image | None = None,
        resolution: str = "1080p",
        storyboards: dict | None = None,
        generate_audio: bool = False,
        seed: int = 0,
    ) -> IO.NodeOutput:
        _ = seed
        if model_name == "kling-video-o1":
            if duration > 10:
                raise ValueError("kling-video-o1 does not support durations greater than 10 seconds.")
            if generate_audio:
                raise ValueError("kling-video-o1 does not support audio generation.")
            if resolution == "4k":
                raise ValueError("kling-video-o1 does not support 4k resolution.")
        stories_enabled = storyboards is not None and storyboards["storyboards"] != "disabled"
        if stories_enabled and model_name == "kling-video-o1":
            raise ValueError("kling-video-o1 does not support storyboards.")
        prompt = normalize_omni_prompt_references(prompt)
        validate_string(prompt, strip_whitespace=True, min_length=0 if stories_enabled else 1, max_length=2500)
        if end_frame is not None and reference_images is not None:
            raise ValueError("The 'end_frame' input cannot be used simultaneously with 'reference_images'.")
        if end_frame is not None and stories_enabled:
            raise ValueError("The 'end_frame' input cannot be used simultaneously with storyboards.")
        if (
            model_name == "kling-video-o1"
            and duration not in (5, 10)
            and end_frame is None
            and reference_images is None

View on GitHub (pinned to 1c6d8d45b3)

Solutions

Set duration to 10 seconds or fewer (5 or 10 are the supported values)
Use a different model for longer image-to-video clips
Generate in segments and concatenate with a video-join node

Example fix

// before
model_name = "kling-video-o1"; duration = 15

// after
model_name = "kling-video-o1"; duration = 10

Defensive patterns

Strategy: validation

Validate before calling

def o1_i2v_duration_ok(model_name: str, duration: int) -> bool:
    return model_name != "kling-video-o1" or duration <= 10

assert o1_i2v_duration_ok(model_name, duration)

Type guard

def i2v_duration_supported(model_name: str, duration: int) -> bool:
    if model_name != "kling-video-o1":
        return True
    return duration <= 10 and duration in (5, 10)  # later branch enforces 5/10

Try / catch

try:
    out = await kling_i2v_node(model_name=model, duration=duration, ...)
except ValueError as e:
    if "does not support durations" in str(e):
        out = await kling_i2v_node(model_name=model, duration=10, ...)
    else:
        raise

Prevention

Cap o1 i2v duration at 10s (use 5 or 10)
For longer i2v, chain clips and join, or switch model

When it happens

Trigger: kling-video-o1 image-to-video with duration set to 15+; workflows migrated from models supporting longer i2v durations.

Common situations: Model swap without adjusting duration; assuming i2v supports t2v's longer-duration tiers.

Related errors

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/e2d58941c695d4ae. Report an issue: GitHub.