Currently doing 6 different Stable Diffusion XL (SDXL) fine tuning (DreamBooth like with 5200 regularization images concept) training. My aim is finding best hyper parameters / configuration for masked training of OneTrainer.
Masked training seriously reduces the overtraining when training dataset is not good enough. However it also makes generated picture body disproportional.
Already done more than 4 trainings and currently 6 trainings are running on 2 L40 GPU.
The GPUs are rented from MassedCompute and we already prepared a template and a guide for this. Guide is not complete yet.
So finding good training hyper parameters / configuration is not easy nor cheap.
You can use A6000 GPU on MassedCompute with our template for only 31 cents per hour. Follow instructions here (still WIP) : https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Tutorials/OneTrainer-Master-SD-1_5-SDXL-Windows-Cloud-Tutorial.md
