# lora anime ai machinelearning deeplearning generativeart digitalart stablediffusion aiart aiイラスト aiイラスト好きさんと繋がりたい ai術師さんと繋がりたい midjourney aiphotography aiportrait waifudiffusion aiartcommunity ai画像 novelai aiartwork catgirl stabledifusion anythingv3 stablediffusionart selfmademodelsandhypernetworks nai novelaidiffusion 東北きりたん きりたんキラキラ金曜日 ずんだもん 東北イタコ

Playing around with and stable diffusion models has been mind-blowing! Currently learning to use the Anything v4.5 model to bring characters and scenes to life.

0 0
2023-03-26


hypernetworks の頃は追加学習ゆーてもこんなものかなー感あったけど

0 1
2023-03-16

This stable diffusion pictures were made with:

1 LORA, 2 hypernetworks, 1 custom model, hiresfix, and anime VAE, and eventually will be upscaled.

2 15
2023-02-08

Hypernetworksで絵柄学習
Loraでキャラ学習

0 0
2023-02-01

hypernetworksに手を出し始めるが、いまいち分かっていないｗ
ブルアカ-アズサ　？



0 4
2023-01-14

Was finishing training small and decently big hypernetworks for "ACertainModel", and to most of other anime models by collateral, for some sort of watercolor style and jsut general appliance today, gonna post couple pics from it. Seem pretty cool.

0 0
2023-01-11

Some comparisons of my four favorite hypernetworks. Have to say that hypernetworks are really one of the best way to integrate consistent new styles into the generation.

0 38
2022-12-02

Testing the "anime_kemonomimi" hypernetwork, I still have to fix some things(I mean photoshop, not the models or the hypernetworks). I like it, what about you?

1 1
2022-11-25

AnythingV3だけど、加工顔面を学習したHypernetworksを当てると、顔には反映されないっぽいけど画風が安定した。効き方が違うのかな？
beautiful woman age XX years oldだけであとはネガティブプロンプトをいれて年代別に
左上18、右上25、左下40、右下60(笑)

1 22
2022-11-20

Some lovely adventurers in my slightly tweaked anime art style. I'm needing to do heavy tweaks to get it where I want. Its slowly being able to do both the princesses and this. Hypernetworks changed the game entirely
Right (new one)

0 25
2022-11-07

hypernetworks
最後に、bikini armor and frill dress でなるほど…という知見を以て、お開きにしたいと思います

0 0
2022-11-04

You've already tried inpainting with different models/hypernetworks? Thats what I do most of the time.

Even with overpainting I still usually find a good hypernetwork and then use inpainting with "Inpaint at full resolution" enabled (bigger = better details)

640x640

0 4
2022-11-04

I want to try to get the hottest girls sans making breasts absurd for a while while keeping a sense of identity. This is my new style and will post in this thread

1 54
2022-11-04

hypernetworksでなんか変わった気がする

0 1
2022-10-29

sure, here's something I did few weeks ago https://t.co/W5gkCsGfq9
I use NAI's default VAE and sometimes use custom hypernetworks made by anons on /g/ as my GPU isn't good enough to make one, default NAI ones don't look very nice imo

2 42
2022-10-27

一枚目の画像のキャラの画像を22枚用意してhypernetworksで学習させた後の出力結果の違い
hypernet str.は0~1の間でどれくらいhypernetworksの効果をつけるか　右に行くほど学習させたデータの絵柄が意識される
一時間程度で人の絵柄を模倣できることがわかる

0 0
2022-10-23


I used the hypernetworks of Kiritan, Zundamon and Itako trained by myself to produce these nice images.

17 57
2022-10-22

Just trained two Mirror's Edge hypernetworks. One is for rooms and environments (left image), while the other is for more abstract art (right image). But feel free to experiment.
Normal - https://t.co/oSiJmb8iqc
Abstract - https://t.co/rFC4twmdIL

1 2
2022-10-20