# novelai stablediffusion aestheticembedding 幽香 textualinversion aiart naotomori 友利奈緒 inktober sciartink sciartink2022 lymedisease sciartinktober lymediseaseawareness sciart medicalart pathology aiartcommunity darkart aiartists nfts

embedding of the style (mostly in regard to coloring) of a certain artist that used to draw Yuuka:
https://t.co/3n45LipS0E
14k & 30k steps, two Colab days' worth. All images generated on 14k.

1 2
2022-10-31

I guess the leaked model is entirely unaware of Asutora under any of his names, so I'll need to attempt training an embedding on 6GB RTX2060.

0 1
2022-10-28

So I picked just five images of acchan for embedding training and the results were better than expected😉

4 44
2022-10-25

最新のAesthetic Embeddingを導入したらまた精度が上がった……！この髪型で横を向いたカードはモバステ両方に無いので大変ヤバでございます……（横を向いてるだけならGaze and Gazeの特訓前がある）

2 4
2022-10-24

aesthetic images embedding の使用を同一シードで試してみます。
1: aesthetic_clip あり aesthetic_text なし
2: aesthetic_clip あり aesthetic_text "beautiful bishoujo"
3: aesthetic_clip なし

0 11
2022-10-22

And voila, its lewd pictures.

Prompt: 1 girl, solo, nude, chained to wall, whipping marks, red hair, dirty skin, cum, tears, dungeon background. Image by <redacted>
Used embeddings: yes | model: wd 1.3 full | sampling method: DDIM 24-32 steps | Upscaler: R-ESRGAN 4x+ Anime6B

0 0
2022-10-19

There are so many variables to take into an account including length/strength of prompt. Dreambooth or embeddings used.
Sometimes it's easiest to plot an x/y matrix to see which one you prefer. I was running some this afternoon.

0 6
2022-10-16

SDのAUTOMATIC1111なんだけど、NovelAIでも使われてるhypernetwork作れるじゃんということで、手元にあったUmeTente-をローカルで学習してみたんだが画風変換やばい。
今後、画風に関してはプロンプト変更しなくて良いという点でEmbeddingよりhypernetworkが主流になってくる予感がする

115 336
2022-10-13

I got too curious, and by doing this I know I'm playing with fire, but I HAD to satiate my curiosity. I feel dirty now. The leaked anime model is really damn good, though the best results likely require using the embeddings files, which don't work on my set-up.

0 0
2022-10-12

fumo embedding works in waifu-diffusion too (no retraining required). WD forgot everything about photos or plushies, but it still understands "make it chibi, give it little T-rex arms and make the sleeves too big".
prompt coherence is way better too (I trained it on booru labels)

1 7
2022-10-12

Aw yeah, thanks to the leak I can now train my own embeddings on the novelai model. It's turning out pretty damn nice! Unlimited wife art, fuck yeah.

7 66
2022-10-08

SciArtInk 2022 prompts are out and these are really good! Day 2 is "Lyme Disease" so we'll go with a nasty Deer Tick embedding itself into an unfortunate host.

1 8
2022-10-05

で、復元したpromptをwaifuに突っ込んだ結果がこう。
悪くはないんだけど、画風の再現とまでは行ってない印象
復元したpromptだと、元のembeddingsを再現するのは難しそうですね

0 7
2022-09-25

Waifu Diffusion+Textual Inversionで試しに服装を学ばせてみたけど、いまいち再現されず微妙……。データには某制服を使ったんだけど色が黒になってしまった（initializer_wordをsuitにしたせい？）。3、4枚目は既存のキャラのembeddingとmergeしたやつで、比較的うまく服装が反映されたやつ。うーむ

1 9
2022-09-22

Experimenting with Textual Inversion. And trained my own embeddings to use to change the style of my pieces to something I've tailored myself using stable diffusion. This is one of my early generations testing it out.

0 8
2022-09-14

1) Learning digital art
2) embedding my own creativity
3) Tried high poly
4) discovered my own creative and unique art style.

Love this journey.

0 2
2022-09-04

Hii! I'm interested, here's an example of another couple comm, I am also embedding my commission sheet link^^
https://t.co/zqIPCwLxNV

0 2
2022-08-10

Interpolating through stable diffusion prompt embedding space while holding the seed fixed.

18 128
2022-08-08

Own the Physical - Claim the Digital

We are embedding chips in all types of apparel inc toys, books & t-shirts

Each chip holds a unique NFT that only that chip can redeem.

With no time-limit as default for redemption, users can keep their stored on the physical pieces

3 5
2022-08-04