Instructions to use MarkBW/golaniyule with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MarkBW/golaniyule with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("MarkBW/golaniyule") prompt = "UNICODE\u0000\u0000b\u0000e\u0000s\u0000t\u0000 \u0000q\u0000u\u0000a\u0000l\u0000i\u0000t\u0000y\u0000,\u0000 \u0000p\u0000h\u0000o\u0000t\u0000o\u0000r\u0000e\u0000a\u0000l\u0000i\u0000s\u0000t\u0000i\u0000c\u0000,\u0000 \u00008\u0000k\u0000,\u0000 \u0000h\u0000i\u0000g\u0000h\u0000 \u0000r\u0000e\u0000s\u0000,\u0000 \u0000f\u0000u\u0000l\u0000l\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000,\u0000 \u00001\u0000g\u0000i\u0000r\u0000l\u0000,\u0000 \u0000w\u0000o\u0000m\u0000a\u0000n\u0000,\u0000 \u00002\u00000\u0000 \u0000y\u0000e\u0000a\u0000r\u0000s\u0000 \u0000o\u0000l\u0000d\u0000 \u0000w\u0000o\u0000m\u0000a\u0000n\u0000,\u0000 \u0000(\u0000c\u0000l\u0000o\u0000s\u0000e\u0000d\u0000 \u0000m\u0000o\u0000u\u0000t\u0000h\u0000:\u00001\u0000.\u00004\u00003\u0000)\u0000,\u0000 \u0000(\u0000s\u0000k\u0000i\u0000n\u0000d\u0000e\u0000n\u0000t\u0000a\u0000t\u0000i\u0000o\u0000n\u0000)\u0000,\u0000 \u0000(\u0000p\u0000o\u0000r\u0000t\u0000r\u0000a\u0000i\u0000t\u0000:\u00000\u0000.\u00006\u0000)\u0000,\u0000 \u0000t\u0000r\u0000e\u0000e\u0000s\u0000,\u0000 \u0000p\u0000a\u0000r\u0000k\u0000 \u0000b\u0000e\u0000n\u0000c\u0000h\u0000,\u0000 \u0000d\u0000a\u0000y\u0000l\u0000i\u0000g\u0000h\u0000t\u0000,\u0000 \u0000(\u0000(\u0000p\u0000a\u0000r\u0000k\u0000 \u0000b\u0000a\u0000c\u0000k\u0000g\u0000r\u0000o\u0000u\u0000n\u0000d\u0000:\u00001\u0000.\u00005\u00002\u0000)\u0000)\u0000,\u0000 \u0000f\u0000u\u0000l\u0000l\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000,\u0000 \u0000(\u0000(\u0000w\u0000h\u0000i\u0000t\u0000e\u0000b\u0000u\u0000t\u0000t\u0000o\u0000n\u0000e\u0000d\u0000s\u0000h\u0000i\u0000r\u0000t\u0000:\u00001\u0000.\u00005\u00008\u0000)\u0000)\u0000,\u0000 \u0000l\u0000o\u0000o\u0000k\u0000i\u0000n\u0000g\u0000 \u0000a\u0000t\u0000 \u0000v\u0000i\u0000e\u0000w\u0000e\u0000r\u0000:\u00001\u0000.\u00008\u0000,\u0000 \u0000(\u00001\u0000g\u0000i\u0000r\u0000l\u0000 \u0000e\u0000y\u0000e\u0000s\u0000 \u0000l\u0000o\u0000o\u0000k\u0000i\u0000n\u0000g\u0000 \u0000a\u0000t\u0000 \u0000v\u0000i\u0000e\u0000w\u0000e\u0000r\u0000:\u00001\u0000.\u00005\u00005\u0000)\u0000,\u0000 \u0000(\u0000m\u0000e\u0000d\u0000i\u0000u\u0000m\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000b\u0000r\u0000o\u0000w\u0000n\u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000p\u0000a\u0000r\u0000t\u0000e\u0000d\u0000b\u0000a\u0000n\u0000g\u0000s\u0000:\u00001\u0000.\u00004\u00005\u0000)\u0000,\u0000 \u0000(\u0000b\u0000o\u0000k\u0000e\u0000h\u0000)\u0000,\u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000A\u0000A\u0000G\u0000-\u0000g\u0000o\u0000l\u0000a\u0000n\u0000i\u0000y\u0000u\u0000l\u0000e\u0000:\u00000\u0000.\u00006\u00009\u0000>\u0000" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
golaniyule

- Prompt
- UNICODEbest quality, photorealistic, 8k, high res, full color, 1girl, woman, 20 years old woman, (closed mouth:1.43), (skindentation), (portrait:0.6), trees, park bench, daylight, ((park background:1.52)), full color, ((whitebuttonedshirt:1.58)), looking at viewer:1.8, (1girl eyes looking at viewer:1.55), (medium hair, brownhair, partedbangs:1.45), (bokeh), <lora:AAG-golaniyule:0.69>
Model description
Use any checkpoint based on SD1.5
its 768,768 image
turn on Hires.fix (or not, please experiment with it yourself)
Hires steps: 10-17, denoising:04-65 ish.. just try it yourself
CGE: 4-7
Use ERSGAN 4X+Anime 6B, DPM++ 2M Karras or DPM++ SDE Karras
Use 20-50 sampling steps
Strength: 0.4-1
I suggest turn off the restore faces check mark for better results of this Lora
She might look like someone from real life, but she is not what you think. She is a totally fictional character.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 2