Type | |
Stats | 930 |
Reviews | (157) |
Published | Jun 12, 2023 |
Base Model | |
Training | Steps: 2,850 Epochs: 19 |
Trigger Words | snow moon ahri |
Hash | AutoV2 B1CEA05ABC |
LoRA trained on Snow Moon Ahri from League of Legends
requested by @Merkuriij
models used
anime: PrimeMix - v2.1, Sweet-mix - v1.8 - flat
2,5D: NijiDiffusedMix - v2.0, PastelDiffusedMix - V2.1, CamelliaMIx_2.5D - V2, ReV Animated
realistic: Paragon V1.0
tags: snow moon ahri, 1girl
optional tags: japanese clothes, pink hair, hair ornament, bare shoulders, fox girl, whisker markings, necklace, energy ball, fox tail
negative embeddings: bad_prompt, negative_hand, ng_deepnegative_v1_75t, bad-artist, EasyNegative
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
for full body shots i recommend using: ComfyUI Impact Pack
or the a1111 alternative GitHub - Bing-su/adetailer