How to use SeeSee21/Z-Anime with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SeeSee21/Z-Anime", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
When using ControlNet, the images generated with the Z-Anime model are pure noise maps.However, I don't encounter this issue when generating images with Z-Image. How should I resolve this situation?
· Sign up or log in to comment
