Full SDXL DreamBooth finetuning, LoRA extraction

In the dreambooth community, it has been empirically shown that extracting a LoRA results in better performance than directly training a LoRA. Enabling a full dreambooth finetune of SDXL would not only enable this functionality, but also further enable users to extract and test out LoRAs of multiple different network ranks without having to rerun the training script multiple times.

Start by locating the repository's SDXL DreamBooth training entry point and the existing LoRA training or extraction support. Read the related implementation and discussion before deciding the scope. Done means users can perform full SDXL DreamBooth finetuning, extract LoRAs, and test multiple network ranks without rerunning training.

Escrito por el modelo de indexación a partir del texto del issue.