README.md

---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=False&allowCommercialUse=RentCivit&allowDerivatives=False&allowDifferentLicense=False
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- skull
- style
- snake
- tattoo
- tiger
- tattoo design
- protoart

base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: proto_tat
widget:
- text: ' '
  
  output:
    url: >-
      23799934.jpeg
- text: ' '
  
  output:
    url: >-
      23799935.jpeg
- text: ' '
  
  output:
    url: >-
      23822007.jpeg
- text: ' '
  
  output:
    url: >-
      23963964.jpeg
- text: ' '
  
  output:
    url: >-
      23800285.jpeg
- text: ' '
  
  output:
    url: >-
      23799130.jpeg
- text: ' '
  
  output:
    url: >-
      23801412.jpeg
- text: ' '
  
  output:
    url: >-
      23799131.jpeg
- text: ' '
  
  output:
    url: >-
      23799132.jpeg

---

# Tattoo Maker XL 

<Gallery />





## Model description

<p>Based on my <a target="_blank" rel="ugc" href="https://civitai.com/models/341334/tattoo-maker?modelVersionId=382132">original tattoo model</a></p><p>Expanded the dataset to include a lot more animals.</p><h2 id="there-is-an-added-amount-of-&quot;pocket-watches&quot;-&quot;roses&quot;-&quot;tigers&quot;-and-&quot;skulls&quot;-in-this-data-set-7mipk1tgx">There is an added amount of "pocket watches", "roses", "tigers", and "skulls" in this data set</h2>

## Trigger words
You should use `proto_tat`, `evang`, `tattoo_style` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/brushpenbob/tattoo-maker-xl/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

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('brushpenbob/tattoo-maker-xl', weight_name='Tattoo_Maker_XL.safetensors')
image = pipeline('`proto_tat`, `evang`, `tattoo_style`').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)