How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ostris/crayon_style_lora_sdxl")

prompt = "an ant holding up a sign that says crayons"
image = pipe(prompt).images[0]

YAML Metadata Error:"instance_prompt" is not allowed to be empty

Crayon Style - SDXL LoRA

Tips

  • No trigger words needed.
  • Converts any prompt into a crayon drawing
  • Strength of 1.0 usually works but you may need to increase or decrease an needed.

Samples

Downloads last month
307
Inference Providers NEW
Examples

Model tree for ostris/crayon_style_lora_sdxl

Adapter
(8390)
this model

Spaces using ostris/crayon_style_lora_sdxl 26