LORA by MANY WAYNE
Collection
3 items • Updated
How to use ManyWayne/OLDDOLL with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ManyWayne/OLDDOLL")
prompt = "Nikon D850 with 105mm f/1.4E lens at f/2.8: [Young woman with glossy, full lips slightly parted, soft glowing caramel-toned skin, and long, wavy black-brown hair cascading around her face, heterochromatic eyes with one amber-gold and the other icy silver, both highly detailed with a glassy, reflective texture, a small black bird tattoo under one eye, sharply defined and arched thick eyebrows, delicate nose piercing, and a neck tattoo that reads 'truth' in stylized script], [smooth and cinematic lighting highlighting the contours of her cheeks and lips], creating a dreamy, surreal quality. High-angle perspective, focus on the subject's face, hyperrealistic 3D-style portrait with ultra-gloss finish, digital illustration style, neutral background."
image = pipe(prompt).images[0]


Hi Bob,
I’ve prepared a very interesting LORA with a doll-like appearance. It was trained on my older works. If you like this style as much as I do, I’m sure it will be a great addition to your LORA collection.
With love, Wayne
In the meantime, you can look at my work. https://www.artstation.com/manywayne
You should use mw3od5 art style by Many Wayne to trigger the image generation.
You should use oldoll to trigger the image generation.
You should use mw doll to trigger the image generation.
Download them in the Files & versions tab.
Base model
black-forest-labs/FLUX.1-dev