-

·
Tsubaki.2 Is Here — Everything You Need to Know
Meet Tsubaki.2 — PixAI’s latest flagship model. Whether you’re crafting atmospheric scenes, bold character art, or complex multi-character compositions, Tsubaki.2 sets a new standard for what’s possible on PixAI. Early Access & Full Release Here’s a full breakdown of what’s new, what’s exclusive, and how to make the most of it. What Makes Tsubaki.2 Different?…
-

·
PixAI Reference Pro Guide— Multi-Image Editing with Natural Language
PixAI Reference Pro is a model designed for image editing through natural language. Instead of generating pictures from a text prompt, this model starts with the images you upload. You give it a photo—or several—and simply describe how you want it changed. The AI reads the characters, poses, outfits, style, layout, and other visual details,…
-

·
LoRA Advanced Techniques: Trigger Words, Multi-Character Generation, and Collection Management
Welcome to our final LoRA guide! In this advanced guide, we’re diving deeper into three crucial topics that will elevate your LoRA mastery: understanding and customizing trigger words, generating multiple characters in a single image, and efficiently managing your growing LoRA collection. Let’s explore these game-changing techniques! 👉 LoRA Beginner’s Guide 👉 LoRA Practical Application…
-

·
How to Train Your Own LoRAs on PixAI: The Complete Creator’s Guide
We’re finally tackling something many of you have been requesting—how to train your own LoRAs on PixAI! Whether you want to bring your original character to life, remake that gorgeous art style you love, or even create the perfect maid outfit LoRA, this comprehensive guide will walk you through the entire process. We’ll focus primarily…
-

·
LoRA Practical Application Guide: Mastering Weight Settings and Advanced Techniques
In our previous guide, we introduced what LoRA is and how it works. Now, it’s time to dive into the practical side of using LoRA! This comprehensive tutorial will walk you through step-by-step examples, explain key concepts like LoRA weight, and share advanced tips to help you get the most out of LoRA. Let’s get…
-

·
LoRA Beginner’s Guide: From Understanding to Application
Welcome to PixAI beginner’s guide on LoRA! This guide will walk you through everything you need to know about LoRA, a powerful tool that allows you to fine-tune AI models to generate specific characters, art styles, and even unique poses without retraining the entire model. 👉 LoRA Practical Application Guide 👉 LoRA Advanced Techniques 👉…
-

·
Master AI Art Models – SDXL
Welcome to our comprehensive guide on AI art models! If you’ve ever wondered how AI creates such stunning artwork, you’ve come to the right place. The magic behind AI-generated art largely comes from something called “models” – and understanding them is key to creating the artwork you envision. In this guide, we’ll explore what models…
-

·
DiT LoRA Training Guide: PixAI’s New Multi-Version Support and Dataset Reuse Features
The PixAI community has been eagerly awaiting enhanced LoRA support for DiT models, and it’s finally here! 🎉 This guide will walk you through all the new features, including multi-version LoRA support, cost-saving dataset reuse, and best practices for DiT LoRA training. 🚀 Full DiTLoRA Support You can now seamlessly use and train LoRAs on…
-

·
Introducing Serin: Your Gateway to Authentic Korean-Style AI Art
Korean visual culture has captivated audiences worldwide through Manhwa comics, Webtoons, and K-dramas. Now, with Serin, you can create authentic Korean-style artwork that captures the distinctive elegance and emotional depth of this beloved aesthetic. What is Serin? Serin is PixAI’s newest in-house generative model, designed to create breathtaking Korean-style character art. Combining the elegance of…
-

·
Introducing Tsubaki: The Revolutionary AI Model That Actually Understands Your Vision | Complete Guide
Ever had that perfect image in your mind, but struggled to get your AI art tool to actually understand what you’re imagining? That’s exactly why we built Tsubaki—our new model that doesn’t just hear your prompts, but truly gets them. Let’s dive into some real examples that demonstrate how our model pushes the boundaries of…
