//=time() ?>
The machine screams (CLIP guided diffusion + text to image embedding prior)
UFOs (CLIP guided diffusion + text to image embedding prior)
Third eye machines (CLIP guided diffusion + text to image embedding prior)
Persephone (CLIP guided diffusion + text to image embedding prior)
Various dark matter space incubator angels (CLIP guided diffusion + text to image embedding prior)
"The goddess of entropy by Wojciech Siudmak, oil on canvas" (CLIP guided diffusion + text to image embedding prior)
"Cyborg goddess, the rise of consciousness, by Wojciech Siudmak, oil on canvas" (I'm trying my ViT-B/32 prior together with the original OpenAI 256x256 ImageNet diffusion model...)
"The Rise Of Consciousness by Gerardo Dottori, oil on canvas" VQGAN+CLIP+prior
Four VQGAN+CLIP outputs for "Moloch whose mind is pure machinery by Greg Rutkowski, oil on canvas", with the new text to image embed converter (prior) I'm training.
Some DIP+CLIP (ViT-B/32) outputs, with the new text embed to image embed converter I'm training: