FLUX-Fill-LoRa-Training and Clip-L training when doing Fine Tuning / DreamBooth with FLUX Dev

There is a repo here which allows you to train FLUX Fill

Can we have it if possible?

Actually Fine Tuning / DreamBooth would be even better than LoRA

https://github.com/Sebastian-Zok/FLUX-Fill-LoRa-Training/tree/main?tab=readme-ov-file

Thank you @kohya-ss

Also can we have Clip-L training when doing Fine Tuning / DreamBooth with FLUX Dev? Currently it is supported with FLUX LoRA

Start with the linked FLUX-Fill-LoRa-Training repository and the existing FLUX LoRA training entry points in this repository. Determine the scope needed for FLUX Fill fine-tuning or DreamBooth and Clip-L training with FLUX Dev, then document the implementation and validation requirements before starting work.

Written by the indexing model from the issue text.