Author: Reverent Elusarca

Workflow source: https://openart.ai/workflows/reverentelusarca/flux consistent character sheet/oSEKBwDLvkt9rHMfdU1b

This workflow uses the SDXL or sd1.5 model as the base for image generation, utilizing ControlNet Pose and IPAdapter for styling. Since Flux does not yet support ControlNet and IPAdapter, this is the current approach.
IPAdapter can be bypassed.
Your ControlNet pose reference image should look like this workflow.
There are two CLIP positive inputs, and both should be the same.
You can use the Upscaler node to achieve better resolution.