This image was created using MultiControlNet, i2i and Inpainting in Stable Diffusion WebUI (AUTOMATIC1111). First, at least 20 images of a man and 20 images of a woman are created, each by applying MultiControlNet (openpose and depth) to 3D drawing doll images of a man and a woman. Next, the selected man and woman are combined using Clip Studio and i2i is applied. Finally, any remaining defects (e.g. hands, legs or eyes) are corrected using Inpainting. The prompts here were used when combining the man and woman and when fixing any defects; the Extra function was used to enlarge the image by a factor of two. Note that the models used were often changed during the procedure. The actual models I used are as follows. HentaiDiffusion_v22 AbyssOrangeMix2_hard grapefruit_v41 7th_anime_v3_A 7th_anime_v3_B 7th_anime_v3_C
Prompt
nsfw, best quality, (1boy:1.4), (yerrow skin: 0.7), denim, nude shirt, short hair, breast sucking, from side, on bed, 1girl, (high resolusion:1.2155), (masterpiece:1.1576), anime coloring, cowgirl position, upper body, (looking at another: 1.4), undressed, bra lift, (oppai loli: 1.4), from side, spread legs, school uniform, (orgasm:1.3), underwear
This image was created using MultiControlNet, i2i and Inpainting in Stable Diffusion WebUI (AUTOMATIC1111). First, at least 20 images of a man and 20 images of a woman are created, each by applying MultiControlNet (openpose and depth) to 3D drawing doll images of a man and a woman. Next, the selected man and woman are combined using Clip Studio and i2i is applied. Finally, any remaining defects (e.g. hands, legs or eyes) are corrected using Inpainting.
The prompts here were used when combining the man and woman and when fixing any defects; the Extra function was used to enlarge the image by a factor of two.
Note that the models used were often changed during the procedure. The actual models I used are as follows.
HentaiDiffusion_v22
AbyssOrangeMix2_hard
grapefruit_v41
7th_anime_v3_A
7th_anime_v3_B
7th_anime_v3_C