---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=1&allowDerivatives=True&allowDifferentLicense=False
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- style
- woman
- man
- hair
- haircut
- hairstyle
- styles
- hairs

base_model: black-forest-labs/FLUX.1-dev
instance_prompt: oxwn_crazy_hair
widget:
- text: ' '
  
  output:
    url: >-
      26476785.jpeg
- text: ' '
  
  output:
    url: >-
      26476797.jpeg
- text: ' '
  
  output:
    url: >-
      26476844.jpeg
- text: ' '
  
  output:
    url: >-
      26476890.jpeg
- text: ' '
  
  output:
    url: >-
      26476946.jpeg
- text: ' '
  
  output:
    url: >-
      26476982.jpeg
- text: ' '
  
  output:
    url: >-
      26476999.jpeg
- text: ' '
  
  output:
    url: >-
      26477045.jpeg
- text: ' '
  
  output:
    url: >-
      26477133.jpeg
- text: ' '
  
  output:
    url: >-
      26477211.jpeg
- text: ' '
  
  output:
    url: >-
      26477214.jpeg

---

# CRAZY HAIR 

<Gallery />





## Model description

<h2 id="here-is-a-lora-model-that-i-primarily-designed-to-achieve-very-expressive-and-voluminous-hair-which-works-well-both-on-photorealistic-images-and-toon-style-characters.-e5p69b1t0"><strong>Here is a LoRA model that I primarily designed to achieve very expressive and voluminous hair, which works well both on photorealistic images and toon-style characters.</strong></h2><p></p><h2 id="training:-2000-steps-n8191n1pp"><strong><span style="color:rgb(181, 181, 181)">Training:</span><span style="color:rgb(250, 82, 82)"> 2000 steps</span></strong></h2><p></p><h2 id="trigger:-oxwn_crazy_hair-7f7g1qvm1"><strong>Trigger: <span style="color:rgb(237, 78, 78)">oxwn_crazy_hair</span></strong></h2><p></p><h2 id="enjoy-!-9rayx4hxu"><strong><span style="color:#228be6">Enjoy !</span></strong></h2>

## Trigger words
You should use `oxwn_crazy_hair` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/Keltezaa/crazy-hair/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('Keltezaa/crazy-hair', weight_name='oxwn_crazy_hair_000002000.safetensors')
image = pipeline('`oxwn_crazy_hair`').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)