//=time() ?>
"(token) as indiana jones, pixar (...)"
1) SD2.1-512 with Textual Embedding
2) SD2.1-768 - dreambooth (shivam)
3) SD1.5-512 - Dreambooth (joepenna)
4) SD2.1-512 Depth model
For each, best of 8
@cloneofsimo More results!
Can't wait someone find a way to convert all the pt file in an usable way for automatic1111 and start using negative prompts.
From my discodiffusion archive. One of the art in my artbook.
Proud GrandPa ☠️
After 15 hours of test, I can dreambooth with SD2 768 using shivam!
1) Follow @DevDminGod tuto: https://t.co/7kGax5zz5M
2) upgrade diffusers to the latest
1/2