New version for Illustrious, trained on a better dataset. Make sure that you follow the trigger words as given for the correct pose. The model is a bit undertrained on purpose to allow for less style bleed.

Use at 0.8 strength for more creativity while still maintaining the pose and style. If you are using this without any other LoRAs, then bump up the strength to 0.9. Using 1 may or may not break your style.

Trigger Words (also refer to the showcase image propmts):

pov, p0vpr1nc4rry, princesscarrypose, carrying person, from above, on side, lying on arms,

(Including "standing" after "1boy" is also helpful for the perspective, although more testing is required),

______

Start with strength 0.75, go upto 0.9. Going higher can change the style, going lower is not tested. Set clip skip to 2 (or don't), as this was trained with clip skip 2. If character face gets in the middle, reduce the weight of the character LoRA by 0.5.

Add "blur, smudged" to your negative prompt. (optional)

Start your prompt with the LoRA trigger words: "Pr1nc3ssC@rry, fr0ntC@rry, 1boy, first person, lying on arms, looking at viewer, dutch angle, 1girl,"

.