PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generation
Models
Studio
NEW
Contest
Create with Mio.2
AI Tools
NEW
Guide

User LoRA

XL

Tsukumizu Yuu / tkmiz Style [Pony XL]

AI Tools
  • AI Anime Generator
  • AI Image Generator
  • AI Animation Generator
  • Anime Figure Generator
  • Character Sheet Generator
  • Magazine Cover Generator
  • Plushie Generator
  • Giant Statue Generator

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
Tsukumizu Yuu / tkmiz Style [Pony XL] - AI Model cover image
Uploaded at
May 12, 2024, 10:31 AM
Uses
3.4k
Reviews
Excellent  (2)
Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

Oga Nadeshiko - AI Model cover image

User LoRA

Oga Nadeshiko
4
Jasmine [Rockman EXE] - AI Model cover image

User LoRA

Jasmine [Rockman EXE]
2
Water Park - Illustrious - AI Model cover image

User LoRA

Water Park - Illustrious
14
Iori Library of Ruina (purple tear) | Illustrious - AI Model cover image

User LoRA

Iori Library of Ruina (purple tear) | Illustrious
5

Description

Makes depressive scribbles similar in style to the artist tsukumizu AKA tkmiz [1][2].How to usePrompt as normal. The dataset was fairly small so it's not an all-encompassing style but it had a decent mix of content including indoor and outdoor shots so it should still be fairly versatile. For more specific prompt tips please see the sample images or uploaded zip with training tags.MISCTrained on Pony SDXL at 1024 resolution with a dataset of 42 mages.All sample images are raw txt2img upscales, no inpainting or helper embeddings used, e.g - your outputs should look better with more than minimum effort.The training was done on a small subset of the artists images, as such the output of this LoRA is not an accurate representation neither in quality or style of the source material. Go support the artist if you want the good stuff.

Comments