# dreambooth stablediffusion algoselfie novelai aiart 幽香 ai textualinversion portrait ブーツ aiartcommunity stablediffusionart aiartist digitalart anythingv3 dreamartist waifudiffusion furryart furry machinelearning

been playing with an Arcimboldo embedding on my drass-optimised model.

0 2
2022-11-29

Some more from first batch.

Lots of optimisation to do, took about an hour of playing about. Prompts here: https://t.co/4soGak9op0 negative important for 2.0 given how we flatten distribution of latents with dedupe etc

Embeddings will make it easier out of the box

2 74
2022-11-28

Trained an embedding to fix the hands.

1 1
2022-11-27

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

0 2
2022-11-25

The last one uses the "asutora_gs31800" embedding coupled with "photorealistic" instead.

1 1
2022-11-22

Perfect hand(s) using Nerfgun3's "bad prompt" negative embedding for stable diffusion. I've been using it for a little while now and can say with out a doubt it works.

0 2
2022-11-22

DreamArtist TI による Embeddings を利用したランス総統

なんか、きれいなジャイアンを思い出す





出力画像 ←→ 学習元画像

0 2
2022-11-20


1 枚の画像からだけでも十分に高精度な Embeddings を作成できるという次世代 Textual Inversion 実装の Dream Artist を試してみた

https://t.co/QXAJA0Oz5Y

素材はランスシリーズ、シィルさんの公式ページの立ち絵
学習回数 4000 Epoch 程度でこの精度よ

生成画像 ←→ 学習元画像

0 2
2022-11-19

Kiriko from Overwatch 2
1.3 embedding
>100 source images, 50k steps
just paste the file into the embeddings folder of the webui and prompt with "kiriko"
https://t.co/FUSoSs518K

0 5
2022-11-19

currently working on a Kiriko embedding!

0 4
2022-11-19

Same parameters but different styles invoked in the prompt, clockwise from top left:
No embedding —> miata8674_gs45000 ⮒
asutora_gs31800 —> (training-in-progress) atawashi_gs22000.
https://t.co/ohCrjIRRbL

1 0
2022-11-19

I tried to recreate Lupe The Wolf from the Archie Sonic franchise using and a custom made embedding, but instead I ended up creating this beauty. ❤️

Lots of inpainting and manual tweaking in Photoshop was done.

1 1
2022-11-17

30/ and & , co-founders of , who were the first to leverage this tech via the project to take the revolutionary step of embedding artist royalities directly into the smart contracts.

3 12
2022-11-16

Hope everyone is doing well!
Still model training, mixing and matching aesthetic embeddings and textual inversions, having a great time!

6 41
2022-11-14

Miata8674 embedding, 33k steps.
I suppose these count as representative samples.

https://t.co/u7zfXjzAeb

0 0
2022-11-09

23k steps @ high CFG.
Either the updates to UI/VAE or the embedding itself don't like it when it's close to something like "perfect face" in the prompt, it really messes with the result. See the first two images. The second pair are better ones...
https://t.co/AxNibT64u4

0 1
2022-11-08

Seems like I didn't after all. The 31,800 steps embedding works fine, but you need to mention its filename in the prompt rather than relying on the init word, which I set to "asutora." I dunno why it only works like that though. ¯\_(ツ)_/¯
https://t.co/jRUDDsFKKs

1 1
2022-11-03

same prompt + Aesthetic embedding: sac_8plus,

0 0
2022-10-31