How to use heldn/Kurdish_FlagSDXL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("heldn/Kurdish_FlagSDXL") prompt = "1boy, hold a Kurdistan_Flag, <lora:Kurdistan_Flag:1>" image = pipe(prompt).images[0]
Chan-Y