Generative AI
2 bite-size cards · 60 seconds each
What is Generative AI?
Generative AI creates new content — text, images, audio, video, code — rather than just classifying or analyzing existing data. ChatGPT writing essays, Midjourney producing images from descriptions, and GitHub Copilot completing code are all generative AI systems, powered by models trained to produce novel outputs.
How Diffusion Models Generate Images: From Noise to Coherent Pictures
Generative image models like Stable Diffusion, DALL-E, and Midjourney don't paint — they denoise. The model learns to reverse a gradual noise-adding process, starting from pure random noise and iteratively refining it into a coherent image guided by a text prompt. The mechanism is surprisingly elegant.
Keep going
Sign up free to get a personalised feed that adapts to your interests as you swipe.
Start for free