🤔🤔🤔

...tried to train my own loRA but never works....it turned out I had to train in dreambooth... weird but I quite happy with the result...

0 1

Someday, I'll know how to work Here's some Braixens, trained on 12 SFW images for 2400 steps (Half 3D, half 2D), with text encoder trained for 50% of the steps, on top of the base 1.5 SD model, with TheLastBen's Colab notebook.🦊

0 3



DreamBooth.
四糸乃.

모델에 상당한 개선이 있었습니다.
モデルにかなりの改善がありました。

0 4



DreamBooth.
四糸乃.

新しくAnything-V3.0modelを使用しました.
새롭게 Anything-V3.0 model을 사용했습니다.

0 14

Death Metal diffusion!
Working on feeding album art into The results are pretty cool so far.

I like how the compositions always work well with a square crop because of the source material.

0 5

Dear 🎨 Issue º7 of is live! Cover art by 🏆 First look at image-to-4D. We talk to about his process and New cover challenge, new chance to win $50 bucks 🔥 https://t.co/h5IPye2yyc

More below 👇

13 91