Generally works better with simpler prompts. It can struggle with hands a little more than other models, even with negative embeddings. Even a little bit of highres-fix can help a lot. I didn't really play around with loras much at the time I was working on it so I don't know how good/bad it is at handling them.
My basic negative prompts are:
EasyNegative, drawn by bad-artist, sketch by bad-artist-anime, (bad_prompt:0.8), (artist name, signature, watermark:1.4), (ugly:1.2)
This help bring out the cartoon aspect that I like from the Samaritan 3d Cartoon model.
Recipe:
Samaritan 3d Cartoon v3
DarkSun v4.1
Weight Sum: 0.25
Calcmode: cosineB