What this workflow does

This workflows is a very simple workflow to use IPAdapter IP-Adapter is an effective and lightweight adapter to achieve image prompt capability for stable diffusion models.

How to use this workflow

The IPAdapter model has to match the CLIP vision encoder and of course the main checkpoint. All SD15 models and all models ending with "vit-h" use the SD15 CLIP vision. One of the SDXL models and all models ending with "vit-g" use the SDXL CLIP vision.

PLUS models use more tokens and are stronger. LIGHT models have a very light impact. FACE and FULL-FACE are only to describe faces (they are not face swap!)