MikuPixAI LoRA
Collection
4 items β’ Updated β’ 1
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]β οΈ NOTE: This is the LEGACY version (V1) of the MikuPix series. It is archived for compatibility and historical use. π Looking for the new & improved version? Check out MikuPix2 (SDXL) for higher fidelity and better anatomy!

MikuPixAI is the original LoRA model trained on Stable Diffusion XL. While it captures the classic Miku aesthetic perfectly, it is now considered an archived model.
MikuPixAI0.6 - 0.77.0Developed by: [M5 Dev]
Base model
stabilityai/stable-diffusion-xl-base-1.0