---
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
- style

base_model: black-forest-labs/FLUX.1-dev
instance_prompt: wat3rc0l0r
widget:
- text: 'wat3rc0l0r, a robot holding a sign that says "I LOVE TOASTERS!"'
  
  output:
    url: >-
      27624879.jpeg
- text: 'young woman in a greenhouse, tending to plants, peaceful, wat3rc0l0r'
  
  output:
    url: >-
      27624011.jpeg
- text: 'wat3rc0l0r, an old man annoyed, looking at the camera'
  
  output:
    url: >-
      27625036.jpeg
- text: 'bohemian painter, laurel wreath, sunset painting session, wat3rc0l0r'
  
  output:
    url: >-
      27624021.jpeg
- text: 'wat3rc0l0r, a couple walking on a dirt road with butterflies in the air'
  
  output:
    url: >-
      27625148.jpeg
- text: 'woman in art studio, canvas, paint-splattered apron, wat3rc0l0r'
  
  output:
    url: >-
      27624125.jpeg
- text: 'lady pirate, tricorn hat, wind-blown hair, defiant grin, wat3rc0l0r'
  
  output:
    url: >-
      27624145.jpeg
- text: ' '
  
  output:
    url: >-
      27633277.jpeg
- text: ' '
  
  output:
    url: >-
      27636055.jpeg
- text: ' '
  
  output:
    url: >-
      27635970.jpeg
- text: 'p0p_r0y, wat3rc0l0r, a pop-art painting of a 50''s rocker cat holding a sign that says "(Cool Cats Use SwarmUI:1.4)" (halftones:1.5)'
  
  output:
    url: >-
      27950743.jpeg
- text: 'tshirt design, my little pony, the style of wat3rc0l0r'
  
  output:
    url: >-
      28437340.jpeg
- text: 'tshirt design, my little pony, the style of wat3rc0l0r'
  
  output:
    url: >-
      28437369.jpeg

---

# Watercolor Sketch Style - FLUX 

<Gallery />





## Model description

<p>Trigger word is <strong>wat3rc0l0r</strong> but I have had good results without the trigger word.. I like to run this at 1.0 but you can lower it to lessen the effect or raise it to 1.3 to really get some unique images. Let me know your thoughts on this lora. I worked really hard and many hours training it with different methods to give you the best lora I possibly could. If you have an idea for a lora shot me a message! <br /></p><p>I use <a rel="ugc" href="https://github.com/mcmonkeyprojects/SwarmUI">SwarmUI</a> for 95% of my image generations and encourage you to try it out! Here's the link to the<a rel="ugc" href="https://github.com/mcmonkeyprojects/SwarmUI"> GitHub repo </a>and also checkout this install video from Kleebz Tech AI to get you started! </p><p></p><p></p><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/vIBTxUZL0Jc?si=ViUYBWZdMswi-c7l" start="0"></iframe></div><p> </p>

## Trigger words
You should use `wat3rc0l0r` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/SouthbayJay/watercolor-sketch-style-flux/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('SouthbayJay/watercolor-sketch-style-flux', weight_name='watercolor_Flux_v3.safetensors')
image = pipeline('tshirt design, my little pony, the style of wat3rc0l0r').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)