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("MarkBW/kaellyn-xl")
prompt = "Kaellyn <lora:Kaellyn-XL:0.8>, ,a woman wearing crop top and high-waisted jeans, harbor,"
image = pipe(prompt).images[0]kaellyn
- Prompt
- Kaellyn <lora:Kaellyn-XL:0.8>, ,a woman wearing crop top and high-waisted jeans, harbor,
- Negative Prompt
- worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art, watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name, airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, 3D ,3D Game, 3D Game Scene, 3D Character
Model description
This lora creates the likeness of French Twitch streamer Kaellyn. Use your favorite realistic model and keep your weight around 0.8
By:Ggrue
Trigger words
You should use kaellyn to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for MarkBW/kaellyn-xl
Base model
stabilityai/stable-diffusion-xl-base-1.0