# aiアート 寧々丸っぽい何か aiart stablediffusion ai wanderer scaramouche 原神 幽香 textualinversion stablediffusion2 redactedasmr redactedaudio milogreer redactedaudiomilo redactedasmrmilo portrait aiartwork dreamstudio

gm
今日も寧々丸教の皆様に良いことがありますように。

そろそろ力技で寧々丸ちゃんを出すでなしにdreamboothなりtextual inversionなりを使って単語を定義したいと思っている今日このごろ。




0 15
2022-12-23

Then I decided to input these images into textual inversion trainer and let it run.

The result was then used to generate new versions of my pieces based on the learned style

These were the results I was looking for...

👇Keep reading

0 1
2022-12-22

イラスト絵への努力とは別にoutpaintやinpaintといった応用的な使い方、画風を別に学習する方法（DreamBooth、Textual Inversionなど）、元絵をベースにimg2imgで仕上げていく方法などがどんどん実用レベルになっていく。このへんで利用ツールとしてはautomatic1111さんのwebuiが広まる。

0 11
2022-12-17

Textual inversion is memory-efficient and fast, but cannot reconstruct with high fidelity,
Dreambooth has high-fidelity, but heavy and overfits unless you have large set of prior preservation.
Can you take the best of both worlds, by Pivotal Tuning in low-rank space? Yes! [1/n]

2 31
2022-12-16

Have some more or less accurate dinosaurs (overall closer to less probably)

Fun fact the sucho and bary's colourschdmes are inversions of eachother because i thought that would be fun

Also returned to something like my old lineart style. I see why i abandoned it.... Haha

1 3
2022-12-14

Futuristic in Cyberpunk City the SD2.1+TEXTUAL INVERSION by inkpunk.... ...not stable yet...still tuning....

0 0
2022-12-10

自前のhypernetworkとtextual inversion有りきのpromptなので、それらを抜くと同一Seedでこんな出力ですがそれでもよければDMします

0 1
2022-12-09

oh he almost said the L word---

this chapter is so precious. those two trying to find a way to protect each other, the inversion of light/dark warm/cold palettes compared to the beginning when Amy was the bright and warm one, etc. so cute

[Webtoon: Space Boy]

0 1
2022-12-08

From 90 to 126k it still produces poor results, but it may be workable. I'll try retraining anyway, I guess. REQUIRES a CFG scale lower than 10 and calling the embedding near the end of the prompt to be adequate.
https://t.co/3n45LipS0E
https://t.co/b8Jh5SPH5U

2 2
2022-12-07

added the lashtalv2 embedding to my ko-fi as a download for members! finetuned via Textual Inversion with love how this one turned out ✨

Link below
↓↓↓

4 53
2022-12-06

& textual inversion. 2.0 really does seem great for customization

7 51
2022-12-02

Despite a very consistent style, the results still fail to match it most of the time at 78k. Besides hair, it also cannot discern the requested color of the vest, which is rather alarming. I may have to retrain it from scratch.
https://t.co/FJbHkWKYbZ

0 0
2022-11-28

. 『反転の天使』
(Angel of Inversion)

1 0
2022-11-28

66k steps with last 10k done at 1.0e-04 learning speed, getting closer and more consistent now.
https://t.co/UEs1bQMVBJ

0 1
2022-11-26

asutora_gs31800 -> no embedding -> miata8674_gs45000 -> atawashi_gs56000
https://t.co/GDA22hOKdt

0 2
2022-11-25

By 56k steps, it still hasn't learned much but the coloring method, and the results are mostly a mess.
https://t.co/0g3ZlCfJKW

0 0
2022-11-25

Training continues, 33k steps now. For some reason it keeps trying to give her yellow hair. The artifacts are severe. Still quite a ways till it's passable even at CFG 8. Fourth pic is with the style invoked last, the rest are early in the prompt.
https://t.co/zDB4ifodHV

2 0
2022-11-22

"I thought I'd try WD with just a textual inversion of myself, this result is too funny and also kind of nice. To all the waifus, hmu!"

0 2
2022-11-20