Works best at 1.0 strength, when mixed with other loras it tends to just stretch out the faces really wide, you have to really give this one a lot of strength to keep the effect in place.

This is mostly for testing and fun, it's not making REAL uv unwrapped faces.

"uv_unwrapp3d_h34d, a woman with long hair. her face is clearly visible"

Purz

Website: https://www.purz.xyz/
Creative Exploration /w Purz: https://www.youtube.com/@PurzBeats
Patreon: https://www.patreon.com/Purz
Twitter/X: https://x.com/PurzBeats
Instagram: https://www.instagram.com/purzbeats/

Trigger words

You should use uv_unwrapp3d_h34d 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('Purz/uv-unwrapped-head', weight_name='purz-uv_unwrapp3d_h34d.safetensors')
image = pipeline('uv_unwrapp3d_h34d, a man with a beard').images[0]

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