This post belongs to a parent (learn more) « hide
Resized to 35% of original (view original)
rumia (touhou) generated by rkkrn using feathermix
Original Commentary AI Metadata

Rumia nude

This is the nude version, which has become a standard for me recently.
I made a little mistake in the process of making it nude, and it affected a few unrelated areas. I think it's safe to say that it's just a slight difference.

I saw a boob about twice as big as this one a while back, so her boobs don't look as good by comparison, but I think they're still big enough.

The LoRA I used this time can be downloaded here:
・https://civitai.com/models/16928/hyperfusion-lora-550k-images
・https://civitai.com/models/80940/rumia-touhou-project
・https://civitai.com/models/49829/watashi-ni-tenshi-ga-maiorita-anime-characters-style
・https://civitai.com/models/123569/body-size-control
・https://civitai.com/models/131093/big-beautiful-nipples
・https://civitai.com/models/11744/huge-nipples
・https://civitai.com/models/39136/large-areolae

Prompt 1girl, solo, rumia, standing, (full body:1.25), in front, closed mouth, smile, (outstretched arms:1.03) BREAK (completely nude:1.0), (plump, thick thighs:1.1), (huge breasts:1.2), (large areolae, huge nipples:1.2), (huge ass:1.03), pussy, (shiny hair:1.03), (shiny skin:1.05), (big eyes:1.01), (pupils:0.87) BREAK medium hair, blonde hair, red eyes, red footwear, mary janes, red hair ribbon BREAK (simple background, white background:1.0) <lora:rumia:0.5:lbw=OUTALL> <lora:hugeNipples_v10:0.3:lbw=OUTALL>
Negative prompt (bad_prompt_version2-neg:0.7), (bad-hands-5:1.2), (low quality, worst quality:1.3), (flat shading:0.97), motion lines, monochrome, multiple views, (ass focus:1.1), sagging breasts, from side, headwear
Sampler Euler
Seed 810835198
Steps 20
Cfg Scale 7
Model Hash de0de03b5f
  • Comments
    •
    rkkrn
    [hidden]

    satanael said:

    Can you tell me what ai software you ise as i want to try to make some ai art similar to what you post here and it would be very usefull to have some data to work off of as a start.

    The software I use for image generation is Stable Diffusion WebUI. I am running this in a Colab Pro environment.
    If you use Colab Pro as I do, I recommend using the notebook at https://github.com/TheLastBen/fast-stable-diffusion.
    The model used to generate this image is feathermix. It can be downloaded from the link in the wiki of this tag.
    I have merged some LoRA into this model and used it.

    3 Reply
    satanael
    [hidden]

    rkkrn said:

    The software I use for image generation is Stable Diffusion WebUI. I am running this in a Colab Pro environment.
    If you use Colab Pro as I do, I recommend using the notebook at https://github.com/TheLastBen/fast-stable-diffusion.
    The model used to generate this image is feathermix. It can be downloaded from the link in the wiki of this tag.
    I have merged some LoRA into this model and used it.

    Thanks I'll download them and see how it goes

    3 Reply