Tensor.Art
Create

NAI3-Pxv Mix/Style [ Pony XL ]

LORA
Reprint

Updated:

pony-v1

No showcase images available, the model won't be visible to others.

709

Why is it called NAI3-Pxv Mix?

  • The dataset was taken from several images on pixiv that were produced using NAI3 AI as well. where the artist mix is definitely used in the generate used in NAI3

  • Number images : 276

How to use (my personal settings):

  • I personally use DPM 2M-Karras because if I use Euler A the color seems pale (I don't know why)

  • Don't forget to use the upscaler

  • Use sd_xl.vae >> Vae recommended on PonyXL

  • "source_anime" is optional, because as long as I tried there was no significant difference (or maybe I didn't realize it)

Issues that may occur:

  • Eyes that are not detailed when producing distant character objects. (A detailer or inpainting is required)

  • Censored images, especially vital parts >> The solution is to use uncensored at the positive prompt

Only compatible with Pony XL or Autism

Version Detail

Pony

Project Permissions

Model reprinted from : https://civitai.com/models/345715

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Comments

Related Posts

No posts yet
Describe the image you want to generate, then press Enter to send.