Type | |
Stats | 969 |
Reviews | (143) |
Published | Aug 21, 2023 |
Base Model | |
Training | Steps: 3,760 Epochs: 10 |
Usage Tips | Clip Skip: 2 |
Trigger Words | athena asamiya, 1girl, red dress, purple hair, puffy short sleeves, hairband, fingerless gloves, earrings, necklace, long hair, sash athena asamiya, 1girl, school uniform, fingerless gloves, hairband, long hair, serafuku, purple hair, purple eyes, star hair ornament, pleated skirt athena asamiya, 1girl, purple eyes, purple hair, long hair, frills, apron, puffy short sleeves, blue dress, hairband, blue bow, wristband |
Training Images | Download |
Hash | AutoV2 72B0696A17 |
LoRA trained on Athena Asamiya from The King of Fighters
requested by: @e0972951006
The pictures that were used for this LoRA also came from him, so thank you for that! :)
anime: YesMix - v1.6 (original), Coffee Donut - 2.1, Dark Sushi Mix 大颗寿司Mix - 2.25D
better hands LoRA: EnvyBetterHands LoCon - beta2
negative embeddings: Fast Negative Embedding (+ FastNegativeV2) - 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