This custom node for ComfyUI allows you to use the Doubutsu small VLM model to describe images. Credit and further information on Doubutsu: [a/https://huggingface.co/qresearch/doubutsu-2b-pt-756](https://huggingface.co/qresearch/doubutsu-2b-pt-756)
https://github.com/EnragedAntelope/ComfyUI-Doubutsu-Describer
git clone https://github.com/EnragedAntelope/ComfyUI-Doubutsu-Describer
comfy node install comfyui-doubutsu-describer