This Lora was trained with the Shampoo Mix V4 model and Shiny Skin Lora only for version "SD1.5"
"Asian" version mixed with VAE (animevae.pt)
"Asian v2" version mixed with VAE (vae-ft-mse-840000-ema-pruned.ckpt)
"Asian Pony" version mix with VAE (vae-ft-mse-840000-ema-pruned.ckpt)
"Asian Pony +VAE" mix version with VAE (animevae.pt)
"Asian Pony +VAEV2.0" mix version with VAE (animevae.pt)
"Shampoo Flux (Asian) mix version with VAE (vae-ft-mse-840000-ema-pruned.ckpt)
Recommended Parameters:
Sampling method: DPM++ SDE Karras, DPM++ 2M Karras, Euler a
Sampling steps: 20 or 30 Steps
Resolution: 768x1152 / 1024x1536
CFG: 3, 5 or 8
Clip Skip: 2
Height: 0.7 or 1.0
Negative prompt:
score_6, score_5_up, score_4_up,
ng_deepnegative_v1_75t,(worst quality:1.4),(low quality:1.4), (normal quality: 1.4),lowres,monochrome,badhandsv5-neg,extra legs,broken leg,bad-hands-5,badhandv4