wizard-s-paper-model-universe

Wizard's Paper Model Universe

<Gallery />

Model description

<p>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.</p><p><span style="color:rgb(193, 194, 197)">Trigger:</span><code>A paper model</code><br /><span style="color:rgb(193, 194, 197)">Add this for styling/control: </span><br /><code>cutout</code><span style="color:rgb(193, 194, 197)">- flat styling </span><br /><code>diorama/peephole</code><span style="color:rgb(193, 194, 197)"> - a layered / framed peephole scene</span><br /><code>vintage</code><span style="color:rgb(193, 194, 197)"> – retro print look</span><br /><code>flat</code><span style="color:rgb(193, 194, 197)">,</span><code>made of paper/cardboard</code><span style="color:rgb(193, 194, 197)"> – if it insists on plastic figures </span><br /><span style="color:rgb(193, 194, 197)">LoRA strength: </span><code>0.8 - 1.2</code><br /><span style="color:rgb(193, 194, 197)">Sampler: </span><code>DDIM Trailing (Substep in some UIs)</code><span style="color:rgb(193, 194, 197)"> </span></p><p><span style="color:#7950f2">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.</span></p><p><span style="color:#7950f2">Love /Wiz</span></p>

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