How to use asparius/ldm-ffhq-256 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("asparius/ldm-ffhq-256", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
I ran the model with 1000 DDIM steps, this is what I get:
You are right, however, I was just learning diffusers. It never meant something serious
· Sign up or log in to comment
