Retroish Anime Style

LORA
Original


Updated:

Original dataset was posted on this bounty and with the permission of AAbrains I used the dataset to make this style using 35 images for 1024 using NoobAI Epsilon-pred 1.1 as a training model

  • Weight: 1-2 adjust depending on which checkpoint you use

  • There aren't any recommended or trigger tags for this style

If you wanna support me or request a commission ko-fi

Additional information:

  • Webui I use

  • MS DPipe fp32 112k Anime VAE SDXL as VAE

  • Sampling method: Euler a

  • Schedule type: Align Your Steps

  • Sampling steps: 24-30

  • Hires steps: 12-15

  • Denoising strength: 0.4

  • Upscale by 1.2-2.0

  • Imagine dimensions vary depending on what I'm trying to do

  • I use 3 to 6 CFG Scale

  • ADetailer for faces

Version Detail

Illustrious
150
50

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts