Landmark 4 stops to get here · leads to 3

Image Generation

Creating new images, often from a text prompt, with generative models such as GANs, VAEs and diffusion models that learn to turn random noise into realistic pictures.

Your route here

4 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Neural Network ✓ understood

    A model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.

  3. Deep Learning ✓ understood

    A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data.

  4. Computer Vision ✓ understood

    The field of AI that gets computers to extract meaning from images and video: what is in them, where it is, and how it moves.

  5. Image Generation · you are here ✓ understood

Picture it

GAN

  • Generator turns random noise into an image
  • Discriminator tries to spot the fakes
  • One forward pass per image

Diffusion model

  • Starts from pure noise
  • Removes noise step by step
  • Text prompt guides each step

VAE

  • Encoder compresses images to a latent space
  • Sample a point in that latent space
  • Decoder turns it back into an image
Notice every approach starts from randomness and learns to shape it into an image; they differ in how that shaping is learned.

Image generation is the task of producing new images rather than analysing existing ones. A generative model learns what a collection of images looks like, statistically, and then produces fresh samples that could plausibly have come from it. Add conditioning, usually a text prompt, and you get text-to-image systems that draw “a lighthouse in a thunderstorm, oil painting” on request.

The hard part is scale. A 512×512 colour image has nearly 800,000 numbers, and almost every random arrangement of them is static. The model has to learn the tiny region of that space where real-looking images live.

Three families

The diagram shows that all three main approaches start from randomness and learn to turn it into an image. They differ in how that transformation is learned.

  • GANs (2014) pit two networks against each other. A generator turns random noise into an image; a discriminator tries to tell its output from real photos. The original paper frames this as a two-player minimax game. GANs are fast, one pass per image, but notoriously unstable to train and prone to covering only part of the data.
  • VAEs (2013) learn an encoder that compresses images into a smooth latent space and a decoder that maps points back to images. Sample a point, decode it, get a new image. Training is stable, but on their own VAEs tend to produce blurry results.
  • Diffusion models learn to reverse a noising process. Training takes real images, adds noise in many small steps, and teaches a network to predict and remove it. Generation starts from pure noise and denoises step by step. The 2020 DDPM paper showed this could produce high-quality images, and diffusion became the dominant approach.

How text-to-image works today

Latent diffusion (2021) made diffusion practical by running it in the compressed latent space of a pre-trained autoencoder instead of on raw pixels, which cut compute sharply, and by adding cross-attention layers so text could steer every denoising step. It is the basis of Stable Diffusion. The prompt is turned into vectors by a text encoder, often one trained to match images with captions, such as CLIP. So a modern system combines a text encoder, a diffusion model and a VAE-style decoder: several of these families working together.

The catch

Generators reproduce the patterns in their training data, biases included. They have historically struggled with fine structure that needs exact consistency, such as legible lettering or the right number of fingers, though each generation of models improves. And because output can now be photorealistic, telling generated images from real ones has become its own problem.

Where it sits

Before this

Computer Vision
Image Generation

Explore nearby

In the research

All papers →

9 papers that build on Image Generation ; showing 5, canon first.

Frontier · Aug 2025 · 875 citations Qwen-Image Technical Report Legible, editable text in generated images was a long-standing weakness; this open model largely fixes it. Frontier · Sep 2025 · 226 citations Seedream 4.0: Toward Next-generation Multimodal Image Generation It set the bar for commercial image generation and editing in one fast system. Frontier · Nov 2025 · 206 citations Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer It shows state-of-the-art image generation does not require “scale at all costs”. Frontier · Nov 2025 · 197 citations SAM 3D: 3Dfy Anything in Images Breaking the 3D data bottleneck makes single-photo 3D practical for real images. Frontier · Aug 2025 · 90 citations Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning More stable RL for image generators, plus a better yardstick for them.

Sources

  1. Goodfellow et al., "Generative Adversarial Networks" . 2014
  2. Ho, Jain and Abbeel, "Denoising Diffusion Probabilistic Models" . 2020
  3. Rombach et al., "High-Resolution Image Synthesis with Latent Diffusion Models" . 2021; CVPR 2022