#image-generation
9 episodes
#2657: How Background Removal Actually Works (and Why It Matters for AI Art)
Background removal isn't magic — it's multiple AI systems working in sequence. Here's what's actually happening under the hood.
#2641: Whiteboard to Clean Diagram with Nano Banana
How Nano Banana finally solves the text rendering problem, turning messy whiteboard photos into polished tech diagrams.
#2546: How AI Editing Tools Actually Delete and Move Objects
The technical stack behind click-to-edit features in tools like Canva and Google Photos — from segmentation to inpainting.
#2544: How to Make AI Architectural Renders Photoreal Without Breaking Geometry
Fixing the uncanny valley in AI-enhanced architectural renders — without breaking the geometry.
#2534: Can AI Generate Diagrams Without Typo Disasters?
Why AI diagram tools still mangle text labels — and what to do about it today.
#2470: Small Model vs Big Model for Prompt Enhancement
When should you fine-tune a tiny model for prompt enhancement instead of prompting a large one? The answer depends on latency, precision, and domain.
#1904: JPEG XL vs AVIF: The Future of Your Photos
Why are blocky sky artifacts still haunting your photos in 2026? We break down the math behind JPEG, WebP, AVIF, and the new JPEG XL.
#551: The LoRA Revolution: Training AI for Personal Perspective
Discover how to train LoRAs for character consistency and unique locations while avoiding common pitfalls like over-fitting and dataset bias.
#46: Pixels, Prompts & Pseudo-Text: AI's Word Problem
AI paints stunning images, but can't spell "cat." Why do advanced models struggle with simple text? Dive into AI's weird word problem!