PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generate
Models
Studio
Contest
Mio.2

Conversational creation

AI Tools
Guide

SDXL

NAI3LikeDiffusion

AI Tools

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • Get the PixAI app
  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Attributions
  • Specified Commercial Transactions Law
NAI3LikeDiffusion - AI Model cover image
Uploaded at
Jul 30, 2024, 11:04 PM
Uses
1.8k
Reviews
Excellent  (2)
Sampling Steps

30

Sampling Method

Euler a

CFG Scale

7

Negative

sketch, worst quality, low quality, deformed, censored, bad anatomy, watermark, signature, 3D, cgi

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

Sunaookami Shiroko/砂狼 シロコ/白子 - AI Model cover image

User LoRA

Sunaookami Shiroko/砂狼 シロコ/白子
5
[illustrious XL]【flyx3】高饱和平涂赛璐璐风格 /Old Fashioned Celluloid -Retro Artstyle - AI Model cover image

User LoRA

[illustrious XL]【flyx3】高饱和平涂赛璐璐风格 /Old Fashioned Celluloid -Retro Artstyle
12
[IL] "We can do it!" / Bras d'honneur / ガッツポーズ - AI Model cover image

User LoRA

[IL] "We can do it!" / Bras d'honneur / ガッツポーズ
11
generate handsome guys !!!!!!!!!!!!!!!!!!!!!!!!!!!!!! - AI Model cover image

User LoRA

generate handsome guys !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
531

Description

NAI3LikeDiffusionYou can test this model for free (unlimited gens, no login required) on EvelAI https://evel.ai, my own model showcase and testing platform.This model merge aims to reproduce the capabilities of NAI3 Diffusion. Main way to get non-generic results is to use artist tags. See preview images for some examples. Aims to produce wide tonal range, high fidelity images without hires fix, upscaling or custom VAEs.This is currently my favourite non-Pony model for anime and weeb stuff.Merge recipe:hs x 0.5 + leekai_ x 0.5 + netaArtXL_v20 - sd_xl_base_1_0.5_0_0_0_0_0_0_0_0_0_0_0_0.5_0.5_0.5_0.5_0_0_0_0_0hs = HyperSpectral, an unreleased perturbation model. Perturbation models are a method I developed to enhance the output of model merges.License:Fair AI Public License 1.0-SD

Comments