WizWhite/wizard-s-wooden-figure-carvings

Wizard's Wooden Figure Carvings

<Gallery />

(CivitAI)

Model description

<p><strong><span style="color:rgb(250, 176, 5)">Wizard's Wooden Figure Carvings</span></strong><span style="color:rgb(250, 176, 5)"><br /></span>A LoRA that makes carved figures in a rough, folk art craft style. <br />Capable of adding nice patina/wear &amp; tear</p><p><span style="color:rgb(193, 194, 197)">Prompt inspiration:</span></p><p><code>W00dn figure carving</code></p><p><code>W00dn figure carving of a XYZ. In a used condition with signs of wear and tear. The hand-painted colors are worn and faded, and the wood has chipped. A large crack in the wood runs through the figure.</code></p><p></p><p><span style="color:rgb(193, 194, 197)">Struggles a bit with abstract concepts and some objects. Will default to white backgrounds unless prompted for something specific, since most of the dataset comes from auction sites.</span></p>

Trigger words

You should use w00dn figure carving 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-wooden-figure-carvings', weight_name='Wiz-W00dn_Figure_Carving.safetensors')
image = pipeline('w00dn figure carving, a grapefruit with a face with bewildered look, donning a Conical Asian hat.
').images[0]

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