Credits To: https://civitai.com/user/AhriMain

Original Description:

Lora trained on Salem from RWBY

models used

anime: MeinaUnreal, CoffeeMix, PrimeMix, ExpMix_Line

2,5D: SoapMix, Lyriel, CamelliaMIx_2.5D_V2, Dark Sushi 2.5D

realistic: fantasticmix_real

salem tags: salem \(rwby\), 1girl, white hair, white skin, cracked skin, red eyes

optional: black dress, long hair

past salem tags: past salem, 1girl, blonde hair, blue eyes, white dress

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: orangemix.vae (for 2,5D pictures), vae-ft-mse-840000-ema-pruned, kl-f8-anime2, blessed2.vae (for anime models)

• Sampler: DPM++ SDE Karras or DPM++ 2M Karras

• Steps: 20

• Clipskip: 2

• Upscaler : img2img in comfyui using 4x-UltraMix_Smooth

• CFG Scale : 5 to 9 (mostly 7 and 8)

• LORA weight for txt2img: 0.5-1

• Denoise strength for img2img: 0.4 to 0.7

If you want the exact same settings, just drag and drop the picture into ComfyUI

for the pictures i used comfyui