Comfy-Org/ComfyUI · error · ValueError

No valid images found in input

Error message

No valid images found in input

What it means

load_and_process_images is the shared loader for the dataset nodes; an empty (or None) image_files list raises immediately because there is nothing to stack into a batch tensor. The function has no silent-empty path by design — an empty dataset would produce a zero-length tensor that breaks downstream batching, so it fails fast with a clear message.

Source

Thrown at comfy_extras/nodes_dataset.py:28

import folder_paths
import node_helpers
from comfy_api.latest import ComfyExtension, io, Input, InputImpl, Types


def load_and_process_images(image_files, input_dir):
    """Utility function to load and process a list of images.

    Args:
        image_files: List of image filenames
        input_dir: Base directory containing the images
        resize_method: How to handle images of different sizes ("None", "Stretch", "Crop", "Pad")

    Returns:
        torch.Tensor: Batch of processed images
    """
    if not image_files:
        raise ValueError("No valid images found in input")

    output_images = []

    for file in image_files:
        image_path = os.path.join(input_dir, file)
        img = node_helpers.pillow(Image.open, image_path)

        if img.mode == "I":
            img = img.point(lambda i: i * (1 / 255))
        img = img.convert("RGB")
        img_array = np.array(img).astype(np.float32) / 255.0
        img_tensor = torch.from_numpy(img_array)[None,]
        output_images.append(img_tensor)

    return output_images


def secure_subfolder_path(base_dir, folder_name):

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Verify the folder actually contains image files and that the extension filter matches them.
2. Fix the folder_name / path so it points at the dataset directory that holds the images.
3. If the empty case is legitimate in your workflow, check the file list before calling the node and skip with a message instead.

Example fix

# before
image_files = [f for f in os.listdir(d) if f.endswith(".png")]  # folder has only .jpg
# after
image_files = [f for f in os.listdir(d) if f.lower().endswith((".png", ".jpg", ".jpeg", ".webp"))]

IMG_EXT = (".png", ".jpg", ".jpeg", ".webp", ".bmp")
def find_images(d):
    files = [f for f in os.listdir(d) if f.lower().endswith(IMG_EXT)]
    if not files:
        raise FileNotFoundError(f"no images in {d}")
    return files

def has_images(files: list) -> bool:
    return bool(files)

When it happens

Trigger: Calling the loader with [] or None, which typically happens after a directory listing filter matched nothing — e.g. the folder exists but contains no image files, or every file was excluded by the extension filter.

Common situations: Pointing LoadDataSet nodes at an empty or misnamed folder; a filter glob that doesn't match (wrong extension case or the folder only has .txt caption files); a previous step moved/renamed the images.

Related errors

• No images provided to create_image_parts; at least one image
• Invalid folder name {folder_name!r}: resolves outside of {ba
• folder_name must name a subfolder of the datasets directory,
• Dataset folder {folder_name!r} not found in: {', '.join(root
• No video files found in {sub_input_dir}

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/8bbeb296c6a84757. Report an issue: GitHub.