How to use HyperX-Sentience/UltraResXL 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("HyperX-Sentience/UltraResXL") prompt = "Ultra-realism, A photograph of a young woman taken from a close-up angle. She has dark, curly hair that is slightly messy and falls around her face. Her skin is fair, and she has dark, well-defined eyebrows. She is wearing a blue denim jacket and a gold necklace. The background is blurred, but there are red and blue lights creating a dramatic atmosphere. The lighting is soft and casts shadows on her face, highlighting her features. The overall mood is intense and moody. JPEG artifacts." image = pipe(prompt).images[0]
