How to use cagliostrolab/animagine-xl-3.0-base with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-3.0-base", dtype=torch.bfloat16, device_map="cuda") prompt = "1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck, masterpiece, best quality" image = pipe(prompt).images[0]
qiuqiu666