How to use KappaNeuro/nicolas-poussin-style 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("KappaNeuro/nicolas-poussin-style") prompt = "Nicolas Poussin Style - Depict a scene of fervor and disruption in the Jerusalem temple. Jesus is at the heart of the scene, brandishing a whip of cords, his expression stern and determined. People are fleeing in all directions - merchants gather their livestock, money changers clutch their scattered coins, and tables lay overturned. Doves are seen escaping, their wings flapping in the air. The temple's intricate architecture is bathed in the soft glow of the setting sun. Use a Nikon D6 DSLR camera with an AF-S NIKKOR 24-70mm f/2.8E ED VR lens for a dynamic shot. The resolution should be 20.8 megapixels, ISO sensitivity: 102,400, and shutter speed 1/8000 second. The style should be ultra-realistic, with a focus on the dramatic lighting and a palette of deep, warm hues." image = pipe(prompt).images[0]
