gildenface-xl-headshot-lora

Gildenface XL – Headshot LoRA

<Gallery />

Model description

<p><strong>Gildenface XL</strong> – a LoRA focused on <em>exaggerated</em> and <em><span style="color:rgb(189, 193, 198)">less-than-glamorous</span></em> close-ups with very <em>high detailed textures</em>.</p><p>Great for producing <em>unique, grotesque and/or outlandish faces</em>, but it can be used as a <em>enhance details for faces and textures</em>, depending on weight and prompt.</p><p><strong>Trigger word: Gildenface</strong><br /><strong>Useful prompt tips:</strong> Portrait photo, close up on face, detailed skin texture, leathery skin texture, visible skin pores, swollen face, greasy hair, wrinkles, potato nose, addict, blushing, chubby, hard shadows, disgusted, blemish, facial hair, staring <br />+ general enhancers, photography terms, and portrait photographers</p><p><strong>Recommended weights:</strong> between 0.8 – 1.2</p><p>It's a bit rough around the edges, and your milage may vary – but when it hits right it's golden.</p><p><span style="color:rgb(193, 194, 197)">Be sure to check out </span><a target="_blank" rel="ugc" href="https://civitai.com/models/181092?modelVersionId=203235">Caricature XL</a><span style="color:rgb(193, 194, 197)"> LoRA by Blink, if you like creating weird</span></p>

Trigger words

You should use Gildenface portrait photo 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

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('WizWhite/gildenface-xl-headshot-lora', weight_name='GildenfaceXL_Headshot_LoRA_v1.safetensors')
image = pipeline('candid close up photo of a surprised Shrek business man, detailed skin texture, standing outside in a swamp,').images[0]

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