>>54973012I'm running Stable Diffusion 1.5. This model:
https://civitai.com/models/24149/mistoonanimeThis lora:
https://civitai.com/models/184009/cynthia-shirona-pokemon-or-goofy-aiThese prompts:
>masterpiece, best quality, Cynthia, blonde hair, long hair, black coat, long coat, bangs over one eye, black pants, heels, hair ornaments, gray eyesI also threw in things like "smile" or "angry" sometimes to get different expressions and stuff. Nothing too complicated. I added in "black pants" after it drew her with the yellow pants and then with blue jeans.
And these negative prompts:
>lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, nsfw, skirt, dress, cape, wings, tail, blue eyes, large breastsCape wings and tail were included in the negative prompts because sometimes the generation seemed to see something long and flowing behind her and turn it into one of those instead of her coat.
I haven't been able to get it to consistently draw her whole outfit right without also fucking up big-picture things like having the right number of limbs in the right places, but I also haven't really been trying to make it "perfect" or even just "good." I'm just dicking around.
