This LoRa is one of my biggest yet, ~500 images for a bit less than 50000 steps x2 (I trained it two times with different settings and merged the results). Its dataset contains mainly modern style illustration+the dataset prevoiusly used for CoolKids LoRa. It should be more flexible (especially at adults themed images) and it should work with a wide variety of subjects. The animals tends to be less humanized but (as you can see in some of the images posted alongside the network) you can mix with my CoolKids LoRa to obtain interesting results. I'll also post a more pastel like/detailed model alongside this, stay tuned
I suggest to use it at ~0.8 weight
I also found that using the word "whimsical" yeld pretty good results, consider incorporating that into your prompts
Training LoRa necessitate a lot of coffee. If you think that what I do is useful and want to help me keep doing this you can buy me a coffe here: https://ko-fi.com/clumsy_trainer