This lora aims to replicate the style Meesh uses from 2017 onwards til about early 2025 where his style switches again.
The Anima version for this is extremely experimental. It's trained locally and basically uses the exact same settings as what I trained the Illustrious version on. It is extremely hit or miss. Struggles with complex poses and concepts, plus has an annoying black border that creeps in (try adding black border to the negatives it might help). I hope both these issues will be solved when run against a proper furry Anima finetune once that's out. Also the sample pics are just using the Meesh lora at either 0.8 or full weight and nothing else on base Anima. I haven't really experimented yet with how best to maximize LoRAs and image quality.