---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- concept
- face
- head
- uv
- purz
- flux1.d
- uv unwrap
- uv unwrapped head
- unwrapped

base_model: black-forest-labs/FLUX.1-dev
instance_prompt: uv_unwrapp3d_h34d
widget:
- text: 'uv_unwrapp3d_h34d, a woman with long hair wearing a black shirt. her face is clearly visible

'
  
  output:
    url: >-
      34075876.jpeg
- text: 'uv_unwrapp3d_h34d, a man with long hair and a beard wearing a black shirt. his face is clearly visible

'
  
  output:
    url: >-
      34075843.jpeg
- text: 'uv_unwrapp3d_h34d, a man with long hair and a beard wearing a black shirt. his face is clearly visible

'
  
  output:
    url: >-
      34075879.jpeg
- text: 'uv_unwrapp3d_h34d, a woman with long hair wearing a black shirt. her face is clearly visible

'
  
  output:
    url: >-
      34075903.jpeg
- text: 'uv_unwrapp3d_h34d a man with a beard and a black shirt against a black background. his facial features are clearly visible'
  
  output:
    url: >-
      34075910.jpeg
- text: 'uv_unwrapp3d_h34d, a man with a beard'
  
  output:
    url: >-
      34075921.jpeg

---

# UV Unwrapped Head 

<Gallery />





## Model description

<p>UV Unwrapped Face - LoRA (Flux.1 D)</p><p></p><p>Trained on images of UV Unwrapped heads.</p><p></p><p>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.</p><p></p><p>This is mostly for testing and fun, it's not making REAL uv unwrapped faces.</p><p></p><p>"uv_unwrapp3d_h34d, a woman with long hair. her face is clearly visible"</p><p></p><p>Purz</p><p>Website: <a target="_blank" rel="ugc" href="https://www.purz.xyz/">https://www.purz.xyz/</a><br />Creative Exploration /w Purz: <a target="_blank" rel="ugc" href="https://www.youtube.com/@PurzBeats">https://www.youtube.com/@PurzBeats</a><br />Patreon: <a target="_blank" rel="ugc" href="https://www.patreon.com/Purz">https://www.patreon.com/Purz</a><br />Twitter/X: <a target="_blank" rel="ugc" href="https://x.com/PurzBeats">https://x.com/PurzBeats</a><br />Instagram: <a target="_blank" rel="ugc" href="https://www.instagram.com/purzbeats/">https://www.instagram.com/purzbeats/</a></p>

## 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](/Purz/uv-unwrapped-head/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
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](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)