license: other
license_name: bespoke-lora-trained-license
license_link: >-
https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Rent&allowDerivatives=True&allowDifferentLicense=False
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- style
- paintingstyle
- paintings
- artist
- artstyle
- painting
- brushstroke
- laclair
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: lclr artstyle
widget:
- text: ' '
output:
url: 2178025.jpeg
- text: ' '
output:
url: 2177023.jpeg
- text: ' '
output:
url: 2177237.jpeg
- text: ' '
output:
url: 2176979.jpeg
- text: ' '
output:
url: 2176998.jpeg
- text: ' '
output:
url: 2177223.jpeg
- text: ' '
output:
url: 2176853.jpeg
- text: ' '
output:
url: 2176922.jpeg
- text: ' '
output:
url: 2177036.jpeg
Painterly LaClair artstyle LoRA 218MB & 1.8GB Versions
Model description
Lightweight 218MB LoRA!
Results can at times not look "ai generated" making this a powerful tool.
Please use responsibly and credit artist Elijah LaClair for his generous usage of his work when possible.
Updated versions of my 0.9XL LoRA.
Trained on the paintings of American Artist Elijah LaClair with his permission.
For the 100 epochs version I followed AI_Characters's guide on LoRA settings but with my own artstyle regulation images as well.
☕ Like what I do? ☕
☕ Buy me a coffee or two! ☕
Trigger words
You should use lclr artstyle
, painting
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
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('DoctorDiffusion/painterly-laclair-artstyle-lora-218mb-1-8gb-versions', weight_name='DD-lclr-artstyle-XL-v1.safetensors')
image = pipeline('`lclr artstyle`, `painting`').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers