Does flux-dev or flux-fill support paired data training for LoRA?

I would like to train a LoRA model for object removal using paired object removal data based on flux-dev or flux-fill. The paired data includes the original image, the mask image of the object to be removed, and the target image (the image after the object has been removed). Does the current code support this? Do you have any suggestions? @lansing @rockerBOO @akx @tsukimiya @wkpark

Start by inspecting the repository's FLUX and LoRA training entry points and documentation for support of paired original, mask, and target images. Determine whether the current training flow accepts this data arrangement; done means a confirmed support status and concrete guidance or a clearly scoped implementation request.

Written by the indexing model from the issue text.