A LoRA to make paper miniature models. Great at creating both flat cardboard scenes as well as 3D paper objects. Has a vintage styling, especially for people and scenes, as the training images are mostly consisting of paper models from 1950s or earlier.

Trigger:A paper model
Add this for styling/control:
cutout- flat styling
diorama/peephole - a layered / framed peephole scene
vintage – retro print look
flat,made of paper/cardboard – if it insists on plastic figures
LoRA strength: 0.8 - 1.2
Sampler: DDIM Trailing (Substep in some UIs)

Please share images to the gallery, it makes this old wizard happier than you would think, to see that people are actually using the LoRAs.

Love /Wiz

Trigger words

You should use A paper model to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('WizWhite/wizard-s-paper-model-universe', weight_name='Wiz-Paper_Model_Universe.safetensors')
image = pipeline('`A paper model`').images[0]

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