video tbaarticle tba previous <a target="_blank" rel="ugc" href="https://civarchive.com/articles/4253/stable-cascade-lora-training-with-onetrainer">(cascade training study)</a>we continue the training study by using the same dataset: <a target="_blank" rel="ugc" href="https://github.com/MushroomFleet/assassinKahb-1024">https://github.com/MushroomFleet/assassinKahb-1024</a> we will use PRODIGY : V1 - used only class tokens for every image "assassinkahb style"V2 - used all the caption pairs found in the dataset as explained we are comparing selected early epochs in the training process for testing, these are marked with "-early".

DJZ AssassinKahb [SDXL test model]

trained with CivitAI on site Lora Trainer, using default settings.

Files with SHA256: 313f62e8e683004b096b07508ad5d3af6bc72c99afc16be6206573abe7243fa6