Diffusers How to use M5-Dev/MikuPixAI 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("M5-Dev/MikuPixAI")
prompt = "MikuPixAI, hatsune_miku, teal twin tails, vocaloid, futuristic outfit, blue eyes, mic headset, eyes in high quality, mouth closed, arr ogant face, bangs straight and closed Hatsune Miku, ultra-detailed anime-style illustration, reclining provocatively on a plush couch in her official turquoise and black uniform with pleated skirt riding up slightly and tie loosened, enhanced bust accentuated by the tight blouse, posing with one leg draped over the armrest and arched back, featuring a teasing gentle sly smile with sultry turquoise eyes, long turquoise twin-tails spread seductively, set in a cozy living room with soft lighting, vibrant turquoise, black, and golden palette, intensely alluring atmosphere, cinematic lighting with sharp highlights on her enhanced chest and curves, highly detailed, 4K resolution, bold and irresistible pose"
image = pipe(prompt).images[0] 
