Hi everyone,this LoRA / LyCORIS was my first try in preparing a dataset and run a training locally on my M1 Max. The training was done with the original SDXL base model.use "humanpup" and/or "pup mask" within the prompt and a CFG of 0.6 to 0.8 (depending on model you are using).The preview image was created by an combination of text2image and inpainting with invokeai.

HumanPup

Welcome to the next iteration of the HumanPup-LyCORIS :) For this version i've used the same data set as in version 0.2 but added some extra steps. Training was done with the vanille SDXL 1.0 as base model over 20 epochs and 4,800 steps in total.As before, my goal is to create a LyCORIS as tool for generating rough drafts and nice adding details via inpainting techniques afterwards.Let me know what you think :)

Files with SHA256: 8b28c26d8f76a5993d7686aba3f88b9145ba6521db360730d89319aca3adb79c