What causes "Up to {SEED_MAX_IMAGES} images are supported per request." in Comfy-Org/ComfyUI?

Reduce the connected images/batches so the total frame count is 20 or fewer (split into multiple Seed node runs and merge text outputs).

Comfy-Org/ComfyUI · error · ValueError

Up to {SEED_MAX_IMAGES} images are supported per request.

Error message

Up to {SEED_MAX_IMAGES} images are supported per request.

What it means

Raised by the ByteDanceSeedNode before any request when the total number of image frames across all connected image inputs exceeds SEED_MAX_IMAGES (20). The node sums get_number_of_images over every connected image tensor (a batched tensor of N images counts as N), so a single 25-frame batch trips it just like 25 separate images.

Source

Thrown at comfy_api_nodes/nodes_bytedance_llm.py:204

            ),
        )

    @classmethod
    async def execute(
        cls,
        prompt: str,
        model: dict,
        seed: int,
        system_prompt: str = "",
    ) -> IO.NodeOutput:
        validate_string(prompt, strip_whitespace=True, min_length=1)
        model_label = model["model"]
        temperature = model["temperature"]
        model_id = SEED_MODELS[model_label]

        image_tensors: list[Input.Image] = [t for t in (model.get("images") or {}).values() if t is not None]
        if sum(get_number_of_images(t) for t in image_tensors) > SEED_MAX_IMAGES:
            raise ValueError(f"Up to {SEED_MAX_IMAGES} images are supported per request.")

        video_inputs: list[Input.Video] = [v for v in (model.get("videos") or {}).values() if v is not None]
        if len(video_inputs) > SEED_MAX_VIDEOS:
            raise ValueError(f"Up to {SEED_MAX_VIDEOS} videos are supported per request.")

        content: list[BytePlusMessageContent] = []
        if image_tensors:
            content.extend(await _build_image_content_blocks(cls, image_tensors))
        if video_inputs:
            content.extend(await _build_video_content_blocks(cls, video_inputs))
        content.append(BytePlusInputText(text=prompt))

        response = await sync_op(
            cls,
            ApiEndpoint(path=BYTEPLUS_RESPONSES_ENDPOINT, method="POST"),
            response_model=BytePlusResponseObject,
            data=BytePlusResponseCreateRequest(
                model=model_id,

View on GitHub (pinned to 1c6d8d45b3)

Solutions

Reduce the connected images/batches so the total frame count is 20 or fewer (split into multiple Seed node runs and merge text outputs).
Use an ImageBatch/ImageConcat node downstream selection, or trim the batch with an image-picker node before connecting.
If you need full-video understanding, pass a VIDEO input instead — video frames are counted separately (max 4 videos).

Example fix

// before: images with 24-frame batch -> Seed node
// after:  trim batch to 20 frames (e.g. ImageCrop/segment nodes) or run two 12-frame requests and combine results

Defensive patterns

Strategy: validation

Validate before calling

SEED_MAX_IMAGES = 20

def total_frames(image_tensors: list) -> int:
    return sum(t.shape[0] if t.ndim == 4 else 1 for t in image_tensors)

# before connecting: assert total_frames(images) <= SEED_MAX_IMAGES

Prevention

Remember the limit counts frames, not tensor inputs — batched tensors count per frame.
Trim large batches (e.g. frame dumps) before wiring into the Seed node.
Split oversized sets into multiple node runs and merge the text outputs.

When it happens

Trigger: sum(get_number_of_images(t) for connected image tensors) > 20 — e.g. one batched IMAGE tensor of 24 images, or several inputs whose frames total more than 20.

Common situations: Feeding a video frame dump or an image grid batch straight into the Seed LLM; daisy-chaining multiple Load Image (batch) nodes; assuming the limit counts tensor inputs rather than frames.

Related errors

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/152e0d3519eb21f9. Report an issue: GitHub.