Alpha Channels, Trimaps, and the Hard Limits of AI Background Removal
Background removal is alpha estimation, not subject detection. Learn how trimaps and matting work, and why hair, glass, and motion blur fail.
AI Image Generation & Editing
Diffusion model architectures, LoRA fine-tuning, prompt engineering for images, and AI-powered image editing workflows.
This theme is curated by our AI council — see how it works.
What topics does this domain cover?
6 topicsEach topic below is a key concept in this domain. Pick any for the full picture: foundations, implementation, what's changing, and risks to consider.
AI-TOOLS
AI Background Removal →
AI background removal uses computer vision models to automatically separate a foreground subject from its background, …
5 articles
AI-TOOLS
AI Image Editing →
AI image editing uses machine learning models to modify existing photos or artwork through text instructions, masked …
6 articles
AI-PRINCIPLES
Diffusion Models →
Diffusion models are a type of generative AI that creates images, video, and audio by learning to reverse a step-by-step …
7 articles
AI-TOOLS
Image Upscaling →
Image upscaling uses AI super-resolution models to increase image resolution while reconstructing realistic detail that …
6 articles
AI-TOOLS
LoRA for Image Generation →
LoRA for image generation is a fine-tuning technique that adds small low-rank weight adapters to a diffusion model to …
5 articles
AI-TOOLS
Prompt Engineering for Image Generation →
Prompt engineering for image generation is the practice of crafting text inputs that reliably produce desired images …
6 articles
Four perspectives on this domain
MONA's articles build your mental model — how things work, why they work that way, and what intuition to develop.
Updated Apr 27, 2026
Concepts covered
Negative Prompts, Weights, Seeds: Image Prompting Limits 2026
Negative prompts and weight syntax aren't universal — and seed reproducibility breaks across model versions. Inside the math of image prompting in 2026.
Prompt Engineering for Image Generation: How Diffusion Models Read Text
Image prompts steer probability, not pixels. Learn how diffusion models, cross-attention, and CFG turn text into images on SD, FLUX, and Midjourney.
What Is AI Background Removal? How Salient Object Segmentation Works
AI background removal is not one model — it's salient object detection plus alpha matting. See how U2-Net, BiRefNet, and SAM 3 cut foregrounds in one pass.
How LoRA Fine-Tunes Diffusion Models for Image Generation
LoRA fine-tunes Stable Diffusion and FLUX without retraining. Learn how rank, alpha, and the BA decomposition turn a few-megabyte file into a new style.
From RRDB Blocks to Diffusion Priors: Inside Modern AI Upscalers
How modern AI upscalers are built — from ESRGAN's RRDB blocks and Real-ESRGAN to SUPIR's diffusion prior, plus the prerequisites you need first.
Training Image LoRAs: Diffusion Math, Rank-Alpha, and VRAM Limits
Image LoRAs retarget diffusion models with small adapter files. Learn the rank-alpha math, VRAM ranges from SD 1.5 to Flux, and why most fail.
What Is Image Upscaling and How AI Super-Resolution Reconstructs Detail Beyond the Original Pixels
AI image upscaling doesn't enlarge what was captured — it generates plausible pixels from a learned prior. Learn how GAN and diffusion super-resolution work.
Why AI Upscalers Hallucinate Faces and Tile Seams at 4K and 8K
AI upscalers don't break at 4K and 8K because of weak hardware. The failures are structural — rooted in diffusion priors and tile-local processing.
From Diffusion to InstructPix2Pix: AI Image Editing Prerequisites
Before using GPT Image or FLUX, understand diffusion, classifier-free guidance, and why InstructPix2Pix made instruction-based editing tractable.
What Is AI Image Editing? Inpainting, Outpainting, Edit Models
AI image editing uses diffusion to modify pixels under a mask or follow text instructions. Learn how inpainting, outpainting, and edit models work.
What Is a Diffusion Model? How Reversing Noise Creates Images and Video
Diffusion models generate images by reversing noise. Learn how forward and reverse processes differ, and why predicting noise became the core training target.
Diffusion Models in 2026: Slow Sampling and Hard Engineering Limits
Why diffusion models still need many sampling steps, why FLUX and SD 3.5 stumble on text and hands, and where the 2026 architecture frontier sits.
U-Net, VAE, Schedulers, and Text Encoders: The Anatomy of a Modern Diffusion Model
A modern diffusion model is not one network but four: a VAE for compression, a U-Net or DiT denoiser, a text encoder, and a sampler. Here is how they fit.
