metadata

library_name: diffusers
pipeline_tag: text-to-image
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
  - art
  - style
  - sdxl
  - lora
  - stable diffusion
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
  - blacklight
  - makeup
  - neon
inference: true

Blacklight Makeup — SDXL LoRA

Blacklight Makeup is a fun art style for SDXL

Difficulty: Advanced (not for beginners)

Blacklight makeup is a mesmerizing art style that I have come to enjoy for its creativity and boldness. The magic lies in its ability to transform a simple canvas, such as the human face and body, into a vibrant and otherworldly masterpiece under the enchanting glow of ultraviolet light. The way the colors pop and come to life creates an almost surreal experience for both the creator and the audience. It's like stepping into a dreamlike realm.

I hope that Blacklight Makeup's radiant glow inspires you to experiment, to challenge norms, and to create beauty that transcends the ordinary!

What's new in Version 2?

I've retrained it with improved captions and parameters, which brings:

simpler trigger words: blacklight makeup
better output quality
reduced file size
improved compatibility with other LoRAs

What's next?

Enhancing the dataset while also experimenting with new training techniques.

How to use:

Example prompt: Portrait of woman with blacklight makeup, fantasy, highly detailed, digital painting, artstation, concept art, sharp focus, illustration, art by Tony Sart and artgerm and randy vargas

trigger words: blacklight makeup
combine with other LoRAs for extra fun!
<lora:blacklight_makeup_v2:1>
2:3 — 832x1248
16:9 — 1360x768
1:1 — 1024x1024

HuggingFace🤗 Diffusers

from diffusers import StableDiffusionXLPipeline, EulerDiscreteScheduler
import torch

pipe = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16,
    variant="fp16",
    use_safetensors=True,
)

pipe.scheduler = EulerDiscreteScheduler.from_config(
    pipe.scheduler.config, use_karras_sigmas=True
)

pipe.to("cuda")

pipe.load_lora_weights(
    "chillpixel/blacklight-makeup-sdxl-lora",
    weight_name="blacklight_makeup_v2.safetensors",
)

image = pipe(
    prompt="Portrait of woman with blacklight makeup, fantasy, highly detailed, digital painting, artstation, concept art, sharp focus, illustration, art by Tony Sart and artgerm and randy vargas",
    num_inference_steps=35,
    guidance_scale=6,
    width=832,
    height=1248,
).images[0]

Also, available at:

I really hope you enjoy this LoRA — and if you do, please click the "like" button!

I will release a new model every time somebody buys me a coffee on Ko-Fi.

Want to hire me to train SDXL? I'm open to innovation and marketing opportunities. Contact me at chillpixelgames@gmail.com