Type | |
Stats | 560 |
Reviews | (97) |
Published | Jul 25, 2023 |
Base Model | |
Training | Steps: 2,420 Epochs: 11 |
Usage Tips | Clip Skip: 2 |
Trigger Words | midnight ahri, 1girl, dress, fur trim, animal ears, cleavage, long hair |
Hash | AutoV2 75387FB7AF |
LoRA trained on Midnight Ahri from League of Legends
requested by: @RosieNuri01
please wait with your request until i finished the remaining ones (Sylas, Super Galaxy Nidalee, Zed)
tags: midnight ahri, 1girl, dress, fur trim, animal ears, cleavage, long hair
add "multiple tails" and "whisker markings" for more characteristics
the short hair version was also in the data set with the tag 'short hair'
anime: YabaL_Mix - V5, Cetus-Mix, Kawaii Realistic Anime Mix
2,5D: Aniverse - Aniverse V1.1, Dark Sushi 2.5D, MeinaUnreal - V4.1, DarkSun - v4.0, ERA_09 - v1.0
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