LoRA trained on Luocha from Honkai: Star Rail

models used

anime: YabaL_Mix V3(image 1,3,4,5,6,7,9,10), MeinaAlter(image 8), PrimeMix - anime(image 2,11,12)

2,5D: HELLmix, DarkSun, MeinaUnreal

tags: luocha, 1boy, blonde hair, long hair

optional tags: white coat, black shirt, white pants, blue ascot, blue armband, blue vest

negative embeddings: embedding:bad-hands-5, embedding:ng_deepnegative_v1_75t, embedding:bad-artist, embedding: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

• Steps: 20 to 35

• Clipskip: 2

• Upscaler : img2img in comfyui using 4xAnimesharp

• CFG Scale : 5 to 9 (mostly 7)

• LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8)

• Denoise strength for img2img: 0.4 to 0.7

im now using 4xAnimesharp for upscaling

for the pictures i used comfyui