Folder Image Captioner with Qwen-VLThis ComfyUI workflow allows you to batch caption entire folders of images quickly and efficiently.It loads images from a selected folder, resizes them if needed, generates high-quality detailed captions using Qwen-VL-Mod (Qwen3-VL-8B-Instruct-Abliterated), and saves both the original image and its corresponding caption file with the exact same filename (e.g., photo.jpg + photo.txt).Ideal for creating training datasets for LoRAs, character fine-tuning, or any project that requires consistent captions.Features:<ul><li>Batch processing directly from folder</li><li>Saves image + caption with the same name</li><li>High detail and accuracy thanks to Qwen-VL</li><li>Maintains the same pose, camera angle, lighting, and location from the original image</li></ul>Required Custom Nodes:<ul><li>ComfyUI Custom Nodes</li><li>Qwen-VL-Mod (or Qwen3-VL-8B-Instruct-Abliterated)</li><li>Resize Image v2</li><li>Load Image Dataset from Folder</li><li>Save Image and Text Dataset to Folder</li></ul>Created by: bobgus39 Original profile: <a target="_blank" rel="ugc" href="https://civarchive.com/user/bobgus39">https://civarchive.com/user/bobgus39</a>Usage: Simply select your image folder and run the workflow. The captions will respect the original pose, camera angle, lighting, and background/location of each image, making them perfect for training consistent characters or scenes.

Files with SHA256: f48ccf79c6e03eff9a93c8429ea5a4e213148ae7c04526e48b66c405fcb2fd47