I removed all the watermarks manually from 100+ images before training, so this won't have the issue other models of the same artist have. Depending on the model you might need to up the strength to higher than 1 numbers or use a higher CFG for the style to show properly.
Some IL models already recognize the artist artstyle, so putting "Andava" on your prompt will give you a really accurate version of the style, but will also bring back the watermark issue, so use a low strength like (andava:0.5).
![chelkyrie's artistic anime style [noob] - AI Model 커버 이미지](https://images-ng.pixai.art/gi/thumb/37f78a8f-fb65-4523-8f25-407a2c7ffb76)