冰之魔妖 the Ice Mayakashi

https://s2.xiaonaofu.top/material/3e969079-ad24-40a8-9318-0b737706d5a9.jpeghttps://s2.xiaonaofu.top/material/196365e0-193b-4d37-91a8-cd0dd7751592.jpeghttps://s2.xiaonaofu.top/material/409a87da-16ab-4533-b1fb-48a1201af8ac.jpeghttps://s2.xiaonaofu.top/material/b3172e03-ad61-4d1a-a2ec-0fbe8b178a5d.jpeghttps://s2.xiaonaofu.top/material/940bfceb-5744-4ac0-b77d-a349c863580c.jpeghttps://s2.xiaonaofu.top/material/32ee28ca-a32b-4a65-98d3-89c92cd38acc.jpeghttps://s2.xiaonaofu.top/material/094cab40-9dd5-435e-84ec-0b59de4a80df.jpeghttps://s2.xiaonaofu.top/material/9f850336-ca89-43f6-a8de-7a06cc9f2d36.jpeghttps://s2.xiaonaofu.top/material/7b457ead-e1a3-452c-8c28-4888e5eebfd3.jpegLoRA for Yuki-Onna the Ice Mayakashi, Yuki-Onna the Icicle Mayakashi, and Yuki-Onna the Absolute Zero Mayakashi
I trained it with 128 pics, which was mainly fan art and some official art. I trained it at 20 epochs with a dim/alpha of 32/16 and with 2 steps.

Please play around with the LoRA weights. Let me know how it goes for you. Read stuff below on guidelines and known issues :)

Triggers:
Form 1 (ie: Ice Mayakashi) : input “YukiOnnaYGO, IceMayakashi, 1girl, pale skin” after the LoRA near the start of the prompt. Consider adding “bare thighs” or “bare legs”.

Form 2 (ie: Icicle Mayakashi) : input “YukiOnnaYGO, IcicleMayakashi, 1girl, pale skin, white bow, sandals, medium breasts” after the LoRA near the start of the prompt. Consider adding “large breasts” or “black pantyhose”.

Form 3 (ie: Absolute Zero Mayakashi) : input “YukiOnnaYGO, AbsoluteZeroMayakashi, 1girl, pale skin, sandals, medium breasts” after the LoRA near the start of the prompt. Consider adding “large breasts”, “black pantyhose”, “holding staff” and “hair ornament”.

NB: can place in negative prompts if the clothes are stubbornly appearing.

Notes:
My experience has shown scale 0.8 ~ 1.1 works best; my best results were 1.

My prompt order shown in the sample pictures worked best for me.

Works on different models though weights may need to change for good results.

I used Anything4.5 model, Ambientmix, anyLora, and Midnight Maple model.

Refer to my pictures for examples and what upscaler I used, keep in mind I have used other textual inversions to help with poses and negatives.

Hide

发表回复

后才能评论