from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('sharaku/verpinscht-v1', weight_name='verpinscht-v1.safetensors')
image = pipeline('A vibrant Disney art style poster featuring the three dogs VRPSCHT. The dogs are playfully posed in the center, with a joyful expression and bright, sparkling eyes that capture its playful spirit. Surrounding the dogs are colorful, whimsical elements like flowers and butterflies, enhancing the cheerful atmosphere. The background is a sunny park scene with lush green grass and a clear blue sky, dotted with fluffy white clouds. The composition is framed with a charming border that includes playful paw prints and colorful accents, creating an inviting and heartwarming visual experience. The name "Verpinscht" is displayed at the bottom of the poster').images[0]
image.save("my_image.png")

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers