How to use ogkalu/Comic-Diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ogkalu/Comic-Diffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
Hello! Which model was this based on? This is useful to know when doing some types of merge. Thanks!
@Swah v1.5 with vae
Thanks @ogkalu ! It's weird, I get better results subtracting 1.4 when merging with another model than I do when I subtract 1.5. But thanks anyway!
· Sign up or log in to comment
