metadata

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
  - lineart
  - vector
  - simple
  - style
  - vector-art
  - vector art
  - complex
  - vector illustration
  - vector style
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: vector
widget:
  - text: ' '
    output:
      url: 3823589.jpeg
  - text: ' '
    output:
      url: 3823606.jpeg
  - text: ' '
    output:
      url: 3822700.jpeg
  - text: ' '
    output:
      url: 3822702.jpeg
  - text: ' '
    output:
      url: 3823587.jpeg
  - text: ' '
    output:
      url: 3822063.jpeg
  - text: ' '
    output:
      url: 3823818.jpeg
  - text: ' '
    output:
      url: 3823823.jpeg
  - text: ' '
    output:
      url: 3823826.jpeg
  - text: ' '
    output:
      url: 3823850.jpeg

Doctor Diffusion's Controllable Vector Art XL LoRA

Model description

This LoRA was trained exclusively on modified and captioned CC0/Pubic Domain images by myself!

USE: "vector" with v2
or
"vctr artstyle" with v1

You can control the level of detail and type of vector art and if there are outlines with these prompts:

For color results use:
"simple details"
"complex details"
"outlines"
"solid color background"

For black and white line art use:
"black line art"
"white background"

Trigger words

You should use vector 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/doctor-diffusion-s-controllable-vector-art-xl-lora', weight_name='DD-vector-v2.safetensors')
image = pipeline('`vector`').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers