---
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
- pencil
- style
- sketch
- traditional art
- traditional media
- pencil art
- theprotoart

base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: evang
widget:
- text: ' '
  
  output:
    url: >-
      20004759.jpeg
- text: ' '
  
  output:
    url: >-
      23801856.jpeg
- text: ' '
  
  output:
    url: >-
      23802076.jpeg
- text: ' '
  
  output:
    url: >-
      20009174.jpeg
- text: ' '
  
  output:
    url: >-
      19956088.jpeg
- text: ' '
  
  output:
    url: >-
      19956083.jpeg
- text: ' '
  
  output:
    url: >-
      19956090.jpeg

---

# PencilXL 

<Gallery />





## Model description

<p>Remaster of my previous <a target="_blank" rel="ugc" href="https://civitai.com/models/20631/ac-pencil?modelVersionId=24553">pencil model</a> now for stable diffusion XL. Trans Am traditional art, pencil sketches meant to re-create that look and aid you in creating references</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/QynE0UGQhRs" start="0"></iframe></div>

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

## Download model

Weights for this model are available in Safetensors format.

[Download](/brushpenbob/pencilxl/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/pencilxl', weight_name='PencilXL.safetensors')
image = pipeline('`evang`, `evang 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)