wizard-s-spellbook-taped-faces

Wizard's Spellbook: Taped Faces

<Gallery />

(CivitAI)

Model description

<p><strong><span style="color:rgb(250, 82, 82)">The Wizard's Face Taping Spell – now available for the general public.</span></strong></p><p><span style="color:rgb(193, 194, 197)">Just start your normal summoning spell with the words; </span><code>s3ll0t4p3</code><span style="color:rgb(193, 194, 197)"> and the magic should appear.</span></p><p><span style="color:rgb(193, 194, 197)">It's not the strongest spell around, so increase your LoRA strength to </span><code>1.2</code><span style="color:rgb(193, 194, 197)"> if the results are not pleasing.</span></p><p><span style="color:rgb(193, 194, 197)">Helpful and supporting prompt words include:</span><br /><code>closeup photograph,</code><span style="color:rgb(193, 194, 197)"> </span><code>selfie,</code><span style="color:rgb(193, 194, 197)"> </span><code>showing teeth,</code><span style="color:rgb(193, 194, 197)"> </span><code>deformed face,</code><span style="color:rgb(193, 194, 197)"> </span><code>squinting eyes,</code></p><p>———————————————————————————</p><p><span style="color:rgb(193, 194, 197)">Special thanks to </span><span data-type="mention" class="mantine-1yiar0p" data-id="mention:580616" data-label="bblink787">@bblink787</span> and his great <a rel="ugc" href="https://civitai.com/models/1129300/windtunnel-face">Windtunnel Face LoRA</a>, that served as inspiration for creating this. Check it out, it's great!</p>

Trigger words

You should use s3ll0t4p3, s3ll0t4p3 closeup photograph 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-spellbook-taped-faces', weight_name='Wiz-Spellbook-Taped_Faces.safetensors')
image = pipeline('Bus stop outdoor ad, depicting a s3ll0t4p3 closeup photograph of a Judge, with distorted face, frowning deeply, unfocused gaze, extremely large nose. The headline reads "WHAT PEOPLE WILL DO FOR BUZZ" in a large font, a small text below reads "Call our hotline 555-80085 for assistance"').images[0]

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