How to use Yntec/DreamlikeDiffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Yntec/DreamlikeDiffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
I love this VAE, I put it in everything, I like how it redraws the eyes. Too bad for this model the eyes don't match, so it was discarded.
· Sign up or log in to comment
