niji5

LORA
Original - TenStar Fund


Updated:

105K

Recommend

  • Lora weight: 0.3 - 0.5 (at 0.6 - 0.8 is heavily style of this Lora and often get undesirable results.)

  • Sampling method: Euler a

  • Sampling Steps: 25 steps

  • CFG scale: 0.5 - 0.8

  • Clip Skip: 2

  • Upscaler: R-ESRGAN 4x+ Anime6B

  • Hires Steps: 15 - 20 steps

  • Resolution (for Upscale): 1024 x 1536 (Actually if you are Pro membership. You can do higher resolution than this if you want)

Support me here: https://buymeacoffee.com/shonzeck34

Version Detail

SDXL 1.0
this version of niji5 is different than previous version. Because I want the style to be more closer to Niji version 5 but not too similar to avoid overfitting. I still not test this version much. But it is good enough for me I guess lol

Project Permissions

Reprinting is strictly prohibited

    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

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.