All example images generated with AutismMix_confetti with Invoke, naively upscaled x2 and face detailed. No extra LoRAs to best demonstrate this model. Better results can definitely be achieved with better upscale/hires fix methods.

All prompts are some variation of:

score_9 score_8_up score_7_up source_furry atherol
solo, male anthro etc
hair style etc
body type etc
clothing etc
background etc
hair colour, eye colour