Choose Your Preferred Model from Abundant Sample Images
See the Diverse Expressive Power of AI Through 315 Illustrations
Hello, this is kojirom.
The 7 models I will introduce today are as follows.
AstolfoMix – Reinforced | Stable Diffusion Checkpoint | Civitai
[Author = 6DammK9]
FiaMix Reboot – v6.5
FiaMix Reboot – v6.5 | Stable Diffusion Checkpoint | Civitai
[Author = Fia_TKTD]
NWMix – final-fp16
NWMix – final-fp16 | Stable Diffusion Checkpoint | Civitai
[Author = neverwinter13]
ReallyNotReal – Ruby
ReallyNotReal – Ruby | Stable Diffusion Checkpoint | Civitai
[Author = CircuitCanvas]
RM01: Experimental Base Merge – v1.0
RM01: Experimental Base Merge – v1.0 | Stable Diffusion Checkpoint | Civitai
[Author = aueki4g467]
ToriUltraAnimeMix – v1.0
ToriUltraAnimeMix – v1.0 | Stable Diffusion Checkpoint | Civitai
[Author = ToriBirdZ]
true_anime_style_2.5d – v1.0
true_anime_style_2.5d – v1.0 | Stable Diffusion Checkpoint | Civitai
[Author = shiroppo]
The prompt I gave them was simple – just one thing:
“1 girl”
“smile”
“embarrassed”
I had them generate these concepts sequentially using the X/Y/Z plot, over and over again.
However, with just “smile” and “embarrassed” the expressions tended to be a bit subdued. So I decided to emphasize these emotions by 1.2 times.
In other words, I described it like this:
(smile:1.2)
(embarrassed:1.2)
I sincerely hope you find some charm in the “normal expressions”, “smiles”, and “embarrassment”.
Now we can spin the gacha wheel many times in hopes of that “one miracle image”.
If this article helps set you on the path to discovering your own miracle image, I couldn’t be happier.
AstolfoMix
FiaMix Reboot
NWMix
ReallyNotReal
Recommended Article
RM01: Experimental Base Merge
大人の妄想を形に！kojiromのR18 CGイラスト集、FANZAで楽しもう！
私、kojiromのCGイラスト集（成人向け）が絶賛発売中です。
あの頃のトキメキをもう一度味わってみませんか。
定価：110円より。
ぜひチェックしてみてください！
true_anime_style_2.5d
Some illustrations may have incomplete details such as hands and fingers. We kindly ask for your understanding.
When using these images, please feel free to crop or modify them as needed.
We encourage you to fully express your creativity and use these illustrations with a free and imaginative approach.
The illustrations featured on this site are available for commercial use.
Stable Diffusion Settings
Here is my attempt at streamlining, then translating the text:
Streamlined:
Below I have included my settings. I used the following configuration to generate the images:
1girl
Negative prompt: easynegative
Steps: 50
Sampler: DPM++ SDE Karras
CFG scale: 5.5
Seed: 693055772
Size: 512×512
Model hash: aab8357cdc
Model: astolfomix_reinforced
VAE hash: 0b204ad0ca
VAE: klF8Anime2_klF8Anime2VAE.pt
Denoising strength: 0.65
Clip skip: 2
Hires upscale: 1.5
Hires steps: 20
Hires upscaler: Latent (bicubic antialiased)
TI hashes: “easynegative: c74b4e810b03”
Eta: 0.667
Version: v1.6.1
X/Y/Z plot
X type = Prompt S/R
X values = 1girl, (smile:1.2), (embarrassed:1.2)
Take care!
English Translation:
Finally, I have included my settings below. I used the following configuration to generate the images:
1girl
Negative prompt: easynegative
Steps: 50
Sampler: DPM++ SDE Karras
CFG scale: 5.5
Seed: 693055772
Size: 512×512
Model hash: aab8357cdc
Model: astolfomix_reinforced
VAE hash: 0b204ad0ca
VAE: klF8Anime2_klF8Anime2VAE.pt
Denoising strength: 0.65
Clip skip: 2
Hires upscale: 1.5
Hires steps: 20
Hires upscaler: Latent (bicubic antialiased)
TI hashes: “easynegative: c74b4e810b03”
Eta: 0.667
Version: v1.6.1
X/Y/Z plot
X type = Prompt S/R
X values = 1girl, (smile:1.2), (embarrassed:1.2)
Until next time, take care!
