Type | |
Stats | 256 |
Reviews | (30) |
Published | Jul 24, 2023 |
Base Model | |
Training | Steps: 4,160 Epochs: 20 |
Usage Tips | Clip Skip: 2 |
Trigger Words | snowmoonkayn, 1boy, asymmetrical clothes, single bare shoulder, heterochromia, horns, headband, black hair, scar, ponytail, fur trim snowmoonshadowassassin,1boy, male focus, white hair, topless male, long hair, gloves, blue eyes, jewelry snowmoonrhaast, monster, male focus, horns, armor, shoulder armor |
Hash | AutoV2 DE095E9042 |
LoRA trained on Snow Moon Kayn from League of Legends
requested by: @MidnightU
please wait with your request until i finished the remaining ones (Midnight Ahri, Firecracker Diana, Sylas, Super Galaxy Nidalee, Zed)
Kayn: snowmoonkayn, 1boy, asymmetrical clothes, single bare shoulder, heterochromia, horns, headband, black hair, scar, ponytail, fur trim
Shadow Assassin: snowmoonshadowassassin,1boy, male focus, white hair, topless male, long hair, gloves, blue eyes, jewelry
Rhaast: snowmoonrhaast, monster, male focus, horns, armor, shoulder armor
anime: YabaL_Mix - V5, Cetus-Mix
2,5D: Aniverse - Aniverse V1.1, Dark Sushi 2.5D, MeinaUnreal - V4.1, DarkSun - v4.0, ReV Animated - v1.2.2
realistic: Paragon V1.0
negative embeddings: Fast Negative Embedding v2
Recommended settings:
Make sure you are aware on the usage instructions of LORA
VAE: vae-ft-mse-840000-ema-pruned (for realistic models & 2,5D), kl-f8-anime2, blessed2.vae (for anime models)
Sampler: DPM++ SDE Karras or DPM++ 2M Karras(euler a for img2img upscaling) from time to time im also using DPM++ 2M alt Karras
Steps: 20 to 35
Clipskip: 2
Upscaler : GitHub - pkuliyi2015/multidiffusion-upscaler-for-automatic1111 4x-UltraSharp(for 2,5D & realistic), 4xAnimesharp(for anime)
CFG Scale : 5 to 9 (mostly 7)
LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8 and 1)
Denoise strength upscaling: 0.3 to 0.55
If you want to autocomplete the tags & trigger im using, I recommend using Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UI
For full body shots i recommend using: ComfyUI Impact Pack
or the a1111 alternative GitHub - Bing-su/adetailer