“When the people of the world all know beauty as beauty, there arises the recognition of ugliness. When they all know the good as good, there arises the recognition of evil.”

Beauty In Evil - by HailoKnight

This lora is created to capture the beauty in the evil creatures of this world.

Things To know:

You should use the trigger word HKEvil
There is a lot of horns in the dataset, if you dont want that add horns to negative prompt.
I can run FLUX locally so my friends over at AIPUB helps me out with the first sample images before I upload it and can use the onsite generator to actually make some more cool art with the lora my self!

Usage Tips :

The LoRA weight I have been using is 0.85, but feel free to try and experiment!
I have used ComfyUI when generated pictures and the settings im using are:
Sampler: dpmpp_3m_SDE
Scheduler: Karras
Steps: 40
cfg: 3.6
Example prompts used XL:
"A woman's face with glowing red eyes and green vines growing on her skin, in the forest, fantasy art style, hyper realistic, cinematic, close up, sharp focus, pov from the side. hkevil. masterpiece, best quality, highly detailed, sharp focus, dynamic lighting"
First image is with my LoRA and second is without my LoRA, same prompt and model.
Example prompts used Pony:
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,(A purple male demon, cracked glowing skin in purple, big purple demon wings on his back, in a dark fantasy style, digital art portrait, pov from the side:1.2) hkevil
Example prompts used Flux:
"A humanoid creature made of intertwined black and red vines, with gray skin, in a dark fantasy style, digital art portrait, pov from the side. hkevil, masterpiece, best quality, highly detailed, sharp focus, dynamic lighting:1.2) hkevil, masterpiece, best quality, highly detailed, sharp focus, dynamic lighting"

Please enjoy and share your amazing work!

Trigger words

You should use hkevil 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

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/beauty-in-evil-by-hailoknight', weight_name='BeautyInEvilFlux.safetensors')
image = pipeline('a cinematic photograph of an male angel warrior with black hair and red glowing eyes wearing dark armor wielding a flaming sword, black and red wings on back, photorealistic, photography lighting, extremely detailed, shot on Sony A7R V with Leica lens, fire background. HKStyle, hkevil').images[0]

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