---
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
- style
- side view
- profile view
- the protoart
- protoart

base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: 
widget:
- text: ' '
  
  output:
    url: >-
      19108819.jpeg
- text: ' '
  
  output:
    url: >-
      19108668.jpeg
- text: ' '
  
  output:
    url: >-
      19108665.jpeg

---

# SIDE XL 

<Gallery />





## Model description

<p>What's up everybody! so this is an updated version of my <a target="_blank" rel="ugc" href="https://civitai.com/models/313598/side-2024?modelVersionId=351853">side profile view model</a> it's main goal is the truth side images of characters. I have to emphasize this because it seem to be confusion from the <a target="_blank" rel="ugc" href="https://civitai.com/models/84286/ac-side?modelVersionId=225962">1.5 model.</a> My goal for this model is for those interested in learning to draw traditionally, or with digital art, and starting off with side profile views was easiest for me.. so I wanted to make a model to replicate a similar look. Trained on traditional hand drawn illustrations using Copic and ohuhu markers, so it tries to replicate that look.</p><p></p><h3 id="i-have-not-tested-this-on-creating-other-things-such-as-vehicles-or-environments-because-again-i-have-to-emphasize-it's-meant-to-create-side-profile-views-of-people-enjoy-and-i-look-forward-to-seeing-the-progress-in-your-art-journey-l51m03wwh">I have not tested this on creating other things such as vehicles or environments because again<strong> I have to emphasize it's meant to create side profile views of people</strong> enjoy, and I look forward to seeing the progress in your art journey</h3><p></p><p>If you would like to try and compare to the previous models, they are linked below</p><p></p><p></p><p>1st version ( and long ago in the time before pickletensors, or LoRa's there was checkpoints... lol has 3 options to test each with slight differences in the training data)</p><p><a target="_blank" rel="ugc" href="https://civitai.com/models/84286/ac-side?modelVersionId=225962">https://civitai.com/models/84286/ac-side?modelVersionId=225962</a></p><p></p><p>2nd version (update LoRa, per request ,combining the data sets from the first and a handful of new images)</p><p><a target="_blank" rel="ugc" href="https://civitai.com/models/313598/side-2024?modelVersionId=351853">https://civitai.com/models/313598/side-2024?modelVersionId=351853</a></p>



## Download model

Weights for this model are available in Safetensors format.

[Download](/brushpenbob/side-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/side-xl', weight_name='SIDE_XL.safetensors')
image = pipeline('Your custom prompt').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)