Visit ComfyUI Online for ready-to-use ComfyUI environment
Automate image copying and organization within workspace for AI artists, part of MinusZone TrainTools suite.
The MZ_ImagesCopyWorkspace node is designed to facilitate the copying and organization of images within a specified workspace. This node is particularly useful for AI artists who need to manage large collections of images for training or other purposes. By automating the process of copying images to a designated workspace, it helps streamline workflows and ensures that all necessary images are readily available in one location. This node is part of the MinusZone TrainTools suite, which aims to provide efficient tools for managing and preparing datasets for AI training. The primary goal of this node is to simplify the image management process, making it easier for you to focus on creative tasks rather than manual file handling.
This parameter specifies the name of the workspace where the images will be copied. It is a required string input, and the workspace name must be unique and non-empty. If the workspace name is not provided or is an empty string, the node will raise an exception. The workspace name helps in organizing and distinguishing different sets of images for various projects or training sessions.
This parameter accepts a list of images in tensor format that need to be copied to the specified workspace. The images are converted to PIL format for processing. This input is optional, and if not provided, the node assumes that the images are already present in the workspace. The images parameter allows you to specify the exact set of images to be managed within the workspace.
This parameter defines the resolution to which the images will be resized before being copied to the workspace. It is an optional integer input with a default value of 1024. Adjusting the resolution can help in standardizing the image sizes for training purposes, ensuring consistency across the dataset.
This parameter is a boolean flag that determines whether the existing images in the workspace should be cleared before copying the new set of images. It accepts values "enable" or "disable", with "disable" being the default. Enabling this option ensures that the workspace is clean and only contains the new set of images, which can be useful for avoiding conflicts or duplicates.
This parameter is a boolean flag that, when enabled, generates the same caption for all images in the workspace. It accepts values "enable" or "disable", with "disable" being the default. This can be useful for quickly annotating a large set of images with a common caption, saving time on manual captioning.
This parameter specifies the caption text to be used when the same_caption_generate flag is enabled. It is a required string input if same_caption_generate is enabled. The caption text is applied to all images in the workspace, providing a uniform annotation for the dataset.
This output parameter provides the directory path of the workspace where the images have been copied. It is a string output that indicates the location of the organized images, allowing you to easily access and manage the workspace for further processing or training.
© Copyright 2024 RunComfy. All Rights Reserved.