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('chau9ho/lala', weight_name='lala.safetensors')
image = pipeline(' a small, fluffy poodle with a soft, curly coat in a light cream color,sitting on a soft, oversized blanket, surrounded by an array of colorful storybooks and plush toys, with a cozy reading nook in the background. The poodle gazes up with a joyful expression, as if inviting you to join in on the adventure. LALA_HK').images[0]
image.save("my_image.png")

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