Use <code>`Kobuichi`</code> in your prompt for best results. Use 0,8-1 strength, with 0,8 being the sweet spot for quality and likeness to the artist. Use 3.5-7 distilled CFG. (3,5=1 CFG) Begging Please, please post images from the model, or like an of mine, lol. Training Details This is very Low Rank LoRA. It was trained on a dataset of 2 images from Kobuichi with 20 repeats and 10 epochs total for training across the dataset.

Files with SHA256: f7f708252e0213f1d1ce9e59eddce078dcabd7ec9d582073f0b0b7fc03572bf1