Preparing Images For LoRa Training (tagging-resizing-cropping)

I use this workflow for managing datasets of images for LoRa training, although there are many other use cases that would benefit from the five groups of tools included in this workflow. The only thing that you would have to do to run this workflow, besides "install missing custom nodes" in the manager, would be to install the QwenVL node from https://github.com/1038lab/ComfyUI-QwenVL there are instructions on the page on how to install it for ComfyUI. This workflow has saved me hours of hand tagging or renaming files when preparing datasets of images and text for LoRa training. Hope it can do the same for you. I have detailed instructions on using the image tagging/captioning section as well as included a handy PowerShell file renaming script to rename your images into uniform names that will match the .txt file names.