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

User LoRA

XL
Style

Pixel Art LoRA [ Noob | IL ]

Create

  • AI Image Generator
  • AI Animation Generator
  • AI Tools
  • Thematic generators
  • Train LoRA
  • Mio.2 Agent
  • Studio

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

  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Specified Commercial Transactions Law
Mio with expression sulk

Oops, this cover can't be shown

It didn't pass our content check — no worries, your model is still fully searchable and usable! Just swap in a cover that works for everyone.

Uploaded at
Jan 10, 2025, 3:53 PM
Uses
610
Reviews
No reviews
Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

⸙⸙⸙ - AI Model cover image

User LoRA

⸙⸙⸙
2
June (Little Einsteins) - AI Model cover image

User LoRA

June (Little Einsteins)
25
my lora - AI Model cover image

User LoRA

my lora
0
Stacia Underwood oshino  - AI Model cover image

User LoRA

Stacia Underwood oshino
0

Description

✨像素画LoRA✨新版本的 Base LoRA 使用了约 3 万张分辨率最高可达 3072×3072 的图像数据集训练了 5 个 epoch,然后在精挑细选的数据集上,通过差分方式微调了多个 Finetuned LoRA,并按一定比例进行了融合。多阶段训练与融合带来了更好的泛化与适应性,实际使用中效果非常不错。SDXL 的 VAE 在潜空间到像素空间的比例为 1:8,因此仅使用本 LoRA 就能直接生成较为规整的像素风图像。若需要更精确的像素风效果,可在生成后使用 NEAREST 算法进行「先 1/8 缩小,再放大」的后期处理,获得严格对齐的像素画。✨Pixel Art LoRA✨This new version of the Base LoRA was trained on approximately 30,000 images (up to 3072×3072 resolution) for 5 epochs. We then applied differential training on a cherry-picked dataset to create multiple fine-tuned LoRAs, which were fused in specific ratios. This multi-stage training and fusion greatly enhance both generalization and adaptability, resulting in excellent performance in real use cases.Because SDXL's VAE has a latent-to-pixel ratio of 1:8, simply using this LoRA can produce neatly arranged pixel art. For stricter pixel alignment, you can apply post-processing by using the NEAREST method to downsample to 1/8 and then upsample back, ensuring a precisely aligned pixel look.日本語版:✨ドット絵LoRA✨新バージョンのベースLoRAは、最大解像度3072×3072の約3万枚の画像データセットを用いて5エポックの学習を行いました。その後、厳選したデータセットをもとに差分方式による微調整を複数のFinetuned LoRAで行い、一定の比率で融合しています。こうした多段階トレーニングと融合により、汎用性と適応性が大幅に向上し、実際の使用でも非常に良好な結果を得られます。SDXLのVAEにおける潜在空間からピクセルへの比率は1:8であるため、このLoRAを使用するだけで整然としたドット絵を生成可能です。より厳密なドット表現が必要な場合は、生成後にNEARESTによる「1/8ダウンサンプリング→アップサンプリング」の後処理を行うことで、ピクセルが正確に揃ったドット絵を得られます。

Comments