Describe a single image or all images in a directory using models such as Janus Pro, Florence2, or JoyCaption (coming soon), with a particular focus on building datasets for training LoRA.
GOAT’d Text Generator 🐐- Turn rough ideas into polished prompts with cloud or local LLMs. Bring images, videos, and audio into the mix, tag them with @, and pick a model-specific prompt guide. Clean text output, ready for your ComfyUI workflow. Big prompt energy, less guesswork.