ZHO-ZHO-ZHO/ComfyUI-Phi-3-mini

feature request: please make a node setup to caption images for training using Phi3v

rafstahelin opened this issue · 0 comments

training SD models requires well captioned dataset images.

I have tested captioning with LMVision node with Claude Opus with very good results. I'd like to expand my research with other vision models. This would be very helpful