Comfy-Org/ComfyUI · error · ValueError

No images provided to create_image_parts; at least one image

Error message

No images provided to create_image_parts; at least one image is required.

What it means

Raised by create_image_parts() when the total image count across all supplied tensors is zero — either an empty list was passed or every tensor has get_number_of_images() == 0. It guards against building a content array with no image parts before any upload happens.

Source

Thrown at comfy_api_nodes/nodes_gemini.py:101

    )
    """,
)


async def create_image_parts(
    cls: type[IO.ComfyNode],
    images: Input.Image | list[Input.Image],
    image_limit: int = 0,
) -> list[GeminiPart]:
    image_parts: list[GeminiPart] = []
    if image_limit < 0:
        raise ValueError("image_limit must be greater than or equal to 0 when creating Gemini image parts.")

    # Accept either a single (possibly-batched) tensor or a list of them; share URL budget across all.
    images_list: list[Input.Image] = images if isinstance(images, list) else [images]
    total_images = sum(get_number_of_images(img) for img in images_list)
    if total_images <= 0:
        raise ValueError("No images provided to create_image_parts; at least one image is required.")

    # If image_limit == 0 --> use all images; otherwise clamp to image_limit.
    effective_max = total_images if image_limit == 0 else min(total_images, image_limit)

    # Number of images we'll send as URLs (fileData)
    num_url_images = min(effective_max, 10)  # Vertex API max number of image links
    upload_kwargs: dict = {"wait_label": "Uploading reference images"}
    if effective_max > num_url_images:
        # Split path (e.g. 11+ images): suppress per-image counter to avoid a confusing dual-fraction label.
        upload_kwargs = {
            "wait_label": f"Uploading reference images ({num_url_images}+)",
            "show_batch_index": False,
        }
    reference_images_urls = await upload_images_to_comfyapi(
        cls,
        images_list,
        max_images=num_url_images,
        **upload_kwargs,

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Verify the upstream image source actually outputs at least one image (inspect it with a Preview Image node).
2. If a filter/picker can legitimately yield zero images, gate the Gemini call on the count (e.g. ImagePadForOutpaint-style switch or a conditional bypass).
3. Fix the empty batch at its source (correct folder, correct mask selection) rather than patching here.

def has_any_images(images) -> bool:
    imgs = images if isinstance(images, list) else [images]
    return sum(img.shape[0] if img.ndim == 4 else 1 for img in imgs) > 0

# skip or bypass the Gemini call when has_any_images(images) is False

When it happens

Trigger: create_image_parts called with an empty list, or with image tensors whose first dimension is 0 (empty batch); typically when an upstream node produced a zero-length batch.

Common situations: An image-picker/filter upstream legitimately matched zero images; a Load Image batch loaded an empty directory; upstream node error swallowed into an empty tensor; branching workflows where one branch has no images selected.

Related errors

• Up to {SEED_MAX_IMAGES} images are supported per request.
• image_limit must be greater than or equal to 0 when creating
• Cannot create grid from empty image list
• INVALID_TAG_FILTER
• Connect at least one keyframe image.

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/45129dcf32ba9c87. Report an issue: GitHub.