AI Image Generation

This is my general guide to AI image generation.

It covers how the models work at a high level, the different types, a bit of history, what you actually get from ChatGPT and how to build image generation into your own code and agents. It’s based on my own experiments calling a handful of image providers from Python. I’ve generated pixel art sprites, photorealistic card table backgrounds and a series of restaurant posters, trying to make one that doesn’t look AI generated. Every image here came from those experiments.

TLDR A short history Six fingers and gibberish text How it works Diffusion models Multimodal models Are multimodal models diffusion under the hood?

How they compare Seeds Types of image generation Ways to use it What you get with ChatGPT What it costs You pay for the canvas Four ways you get billed The landscape in October 2026 Cost per usable image Prompting that works Describe the camera, not the view Marketing is where AI images get the most criticism Making a poster that doesn’t look AI generated Prompting rules of thumb Pixel art Pixel art is a style, not a format Many sprites on one canvas Doing pixel art properly Where the line falls Integrating image generation into a coding project Put a thin interface in front of every provider Expect the ground to move Log everything Treat generation as a slow, failing job Do the exact work in code Test without spending money Integrating with an agent Claude doesn’t generate images Three ways to wire it up How the experiments in this guide were run Tips for agent-driven generation Glossary Resources TLDR Most models start from noise and clean it up. Text steers the clean-up. Newer models also plan the image the way a chat model plans a sentence. You pay for the canvas, not the content. A plain wooden table costs the same as a detailed oil painting of the same size. ChatGPT is the easiest way in and the hardest to control. Great for one-off images and conversational edits. For anything repeatable you want the API. Prices vary more than 100 times over. Anything from a fraction of a cent to 15 cents or more per image. Running a model locally costs nothing. The cheapest model isn’t always the cheapest result. The APIs move under you. Models get retired with weeks of notice and providers quietly ignore parameters. Keep the model in config and log what you actually got back. Describe how it was made, not how it should look. Camera, film, print process and layout get better results than “stunning” and “hyper-detailed”. Spelling and fingers are no longer the giveaway. The tell now is taste. Too much glow, too much drama and nothing allowed to be plain. Agents are good at this. A multimodal agent can write the prompt, call the API, look at the result and try again. You still need to supply the taste. The best pipelines are hybrids. Let AI do the creative part. Let ordinary code do the exact parts like sizing, transparency, palettes and layout. A short history 2014 - GANs. Ian Goodfellow’s generative adversarial networks pit two networks against each other, one making images and one spotting fakes. They go on to produce convincing synthetic faces but are hard to steer with text. 2015 - DeepDream. Google’s Inceptionism experiments turn image recognition inside out. The results are full of psychedelic dog faces, because the network was trained on a dataset with a lot of dogs in it. 2018 - AI art goes to auction. A blurry GAN portrait called Edmond de Belamy sells at Christie’s for $432,500, more than 40 times its top estimate. 2019 - Faces that don’t exist. NVIDIA’s StyleGAN powers thispersondoesnotexist.com, a new photorealistic fake face on every refresh. 2021 - DALL-E. OpenAI links text and images in one model. You can type a sentence and get a picture, even if it’s a small, blurry one. 2022 - The breakout year. DALL-E 2, Midjourney and Stable Diffusion all arrive within a few months. Stable Diffusion is open source and runs on a gaming PC with about 7GB of video memory, which kicks off a huge community of fine-tunes and tools. 2023 - Photorealism and readable text. A Midjourney image of the Pope in a white puffer jacket fools much of the internet. Ideogram launches with text you can actually read. SDXL raises the bar for open models and DALL-E 3 moves into ChatGPT. 2024 - Flux and the backlash. Former Stable Diffusion researchers found Black Forest Labs and release Flux, which becomes the default open-weight model. Meanwhile AI posters become a byword for cutting corners (more on that below).

2025 - Native image models.

OpenAI builds image generation into GPT-4o itself and the “Studio Ghibli” trend takes over social media. Google’s Gemini 2.5 Flash Image, nicknamed Nano Banana, makes conversational editing cheap at $0.039 an image. 2026 - Abundance and churn. OpenAI switches off DALL-E in its API. OpenRouter alone lists over 60 image models from a dozen companies, and older models are retired every few months. Six fingers and gibberish text For a few years the easiest way to spot an AI image was to count the fingers or try to read the sign in the background. Both problems are now mostly fixed, and why they happened says a lot about how these models work. Hands are complicated, flexible and usually partly hidden in photos. Behind a cup, in a pocket, half out of frame. The models learned what hands look like as a texture, not how many fingers they have. Midjourney v5 in March 2023 was widely reported as the turning point. Experts suspected better curated training data with clearer pictures of hands, plus bigger models and higher resolutions.

It wasn’t perfect.