Generative Media

Models that make images, video and sound: GANs, diffusion and beyond. 58 entries live here, and 101 from other domains touch it.

Essential

AI artImages, music or other artworks made with the help of AI — from early computer drawing programs to today's prompt-based image generators — and the debate over whether and how such work counts as art.
diffusion modelAn AI that learns to create images, sound or video by practicing noise removal: shown pictures buried under static, it learns to clean them up, then builds new ones starting from pure static.
MidjourneyA popular paid AI image generator, first used by typing prompts into the chat app Discord, known for its polished, painterly look; it can also animate images into short videos.
Stable DiffusionA widely used image-generating AI whose model files were released for anyone to download, so people could run it on their own computers and adapt it.
text-to-image modelAn AI system that creates a picture from a written description, such as 'a fox reading a newspaper, in watercolor', usually within seconds.
text-to-video modelAn AI that creates a short video clip — increasingly with matching sound — from a written description, such as 'a paper boat sailing down a rainy street'.
voice cloningUsing AI to copy a specific person's voice from recordings, so a computer can say new things that sound like them — useful for dubbing and accessibility, and abused in scams.

All other entries

autoregressive image generationMaking a picture one piece at a time, each piece predicted from those already made — the way chatbots write text word by word.
classifier guidanceA way to push a diffusion image generator toward a requested category by consulting a separate image-recognition model at every step, trading variety for images that more clearly show the target.
classifier-free guidanceA setting that makes an image generator follow the prompt more strictly by comparing what it would draw with and without the prompt, then exaggerating the difference.
CLIP scoreA score for how well a picture matches a text description, computed by an AI model that was trained to pair images with their captions.
consistency modelA generator trained to jump from noise straight to a finished image in one step, instead of the dozens of small steps a diffusion model normally takes.
ControlNetAn add-on for image generators that makes them follow a guide image — a sketch, a stick-figure pose or a depth map — so the layout comes out as intended.
DALL·EOpenAI's pioneering series of image generators, named after the painter Salvador Dalí and the robot WALL·E, which showed in 2021–2023 that AI could draw almost anything described in words.
DeepDreamA 2015 Google program that exaggerates whatever patterns an image-recognition network detects in a picture, producing hallucinatory images full of eyes, dog faces and swirls.
denoising diffusion implicit modelA faster way to run a diffusion image generator that skips most of the steps and, for the same starting noise, always gives the same picture.
denoising diffusion probabilistic modelThe 2020 recipe that made diffusion image generators work well: add noise to pictures over a thousand small steps, then train a network to guess the noise so it can be removed.
diffusion distillationTraining a fast image generator to imitate a slow diffusion model, so that a picture that once took fifty steps can be made in one to four.
diffusion samplerThe step-by-step routine a diffusion model follows to turn noise into a finished picture; the choice of sampler and number of steps trades speed against quality.
diffusion transformerA diffusion image or video generator whose core network is a transformer — the architecture behind chatbots — instead of the older image-specific design, which lets it improve more predictably as it grows.
DreamBoothA way to teach an image generator one specific subject — your dog, your face, a product — from a handful of photos, so it can draw that exact subject in new scenes.
evidence lower boundA quantity that is always less than or equal to how well a model explains its data, but much easier to calculate; pushing it upward is how models such as VAEs learn.
flow matchingA way to train generators that learns, for every point between random noise and real data, which direction to move, so that noise can be steered smoothly into new examples.
FLUXA family of image-generating AI models from the German start-up Black Forest Labs, founded by researchers behind Stable Diffusion; some versions can be downloaded and run freely.
Fréchet inception distanceA score for image generators that compares the overall statistics of their pictures with those of real photos, as seen by an image-recognition network; lower is better.
generative adversarial networkTwo neural networks trained as rivals: one forges fake images, the other tries to spot the fakes. As both improve, the forger's output becomes realistic enough to fool people.
generative modelA model that learns what a kind of data looks like — faces, sentences, songs — well enough to produce new examples that resemble the originals without copying them.
image tokenizerA component that chops a picture into a short sequence of 'visual words' that a language-style AI model can read or write, and turns such sequences back into pictures.
ImagenGoogle's family of AI image generators, first shown in 2022, whose research showed that better understanding of language yields pictures that match descriptions more faithfully.
image-to-image translationTurning one picture into another version of itself — a sketch into a photo, a day scene into night, a horse into a zebra — while keeping its layout.
Inception scoreAn early score for image generators that rewards pictures an image-recognition network can label confidently and a collection that covers many different labels; higher is better.
inpaintingFilling in a missing or erased part of a picture so it blends seamlessly with the rest — removing a stranger from a photo, or repairing a damaged one.
instruction-based image editingChanging a picture by telling an AI what to change — 'make it night', 'remove the car', 'give her a red coat' — instead of using editing tools by hand.
latent diffusion modelA diffusion image generator that works on a shrunken, compressed version of each picture instead of the full-size pixels, which makes it far cheaper to train and run.
mode collapseWhen a generator gets stuck producing only a few kinds of output — the same face, the same joke — instead of the full variety it was meant to learn.
music generationUsing AI to compose or produce music — from melodies written as notes to complete songs with vocals — often from a short text description like 'upbeat jazz with saxophone'.
Nano BananaThe nickname, later Google's official branding, for its Gemini image models, a viral hit in 2025 for editing photos from simple instructions while keeping people looking like themselves.
negative promptA second prompt listing what you do not want in a generated image — 'blurry, extra fingers, watermark' — which the generator then steers away from.
neural audio codecA neural network that squeezes sound into a very compact stream of numbers and rebuilds it, used both to send audio cheaply and to let AI models 'write' speech and music piece by piece.
noise scheduleThe plan for how much static is mixed into training examples at each step of a diffusion model, from almost none to total noise; its shape affects quality and speed.
normalizing flowA generator built from a chain of reversible steps that reshape simple random noise into realistic data; because every step can be undone, it can also calculate exactly how likely any example is.
perceptual lossA way of judging how different two images look to a person by comparing what a trained image-recognition network 'sees' in each, instead of comparing pixels one by one.
random seedA number that fixes the 'random' choices a computer makes; reuse the same seed and settings, and an image generator produces the same picture again.
rectified flowA generator trained to move random noise toward real data along straight lines, which can then be straightened further so that a picture comes out in one or a few steps.
reparameterization trickA trick that rewrites a random draw as fixed numbers plus separate, outside randomness, so that a neural network can still learn through a step that involves chance.
score distillation samplingA trick for creating 3D objects from a text description by repeatedly asking a 2D image generator whether pictures of the object, seen from many angles, look right — and adjusting the object until they do.
score-based generative modelA generator that learns, for any noisy example, which direction would make it look more like real data — then starts from pure noise and follows those directions step by step.
SoraOpenAI's video-generating AI, unveiled in 2024 with startlingly realistic clips; a 2025 version added sound and a social app, but OpenAI shut the service down in 2026.
style transferRepainting a photo in the style of an artwork — your street as Van Gogh might have painted it — by keeping the photo's content and borrowing the painting's colors, strokes and textures.
StyleGANAn image-generating network from NVIDIA, famous for photorealistic faces of people who do not exist, that sets coarse traits such as head angle and face shape separately from fine details such as coloring and skin texture.
SunoA popular AI service that writes and performs complete songs — music, lyrics and singing — from a short text description.
super-resolutionMaking a small or blurry image larger and sharper by having AI fill in plausible fine detail, rather than just stretching the pixels.
textual inversionTeaching an image generator a new 'word' for a specific object or style from a few example pictures, leaving the model itself unchanged — only one vocabulary entry is added.
variational autoencoderA neural network that learns to squeeze data into a compact, slightly fuzzy code and rebuild it, arranged so that decoding random codes produces new, plausible examples.
VeoGoogle's video-generating AI, which since 2025 creates short clips complete with matching sound and dialogue from a written prompt.
VQGANAn image compressor that turns a picture into a small grid of codebook 'tiles' while keeping it sharp, used as the vocabulary of many image generators and of an early wave of AI art.
VQ-VAEA network that compresses an image or sound into a short list of entries from a learned 'codebook' — like describing a picture with a fixed set of tiles — which other models can then generate.
Wasserstein GANA version of the forger-versus-detective image generator that measures how far its fakes are from real data in a smoother way, making training steadier and easier to monitor.

Also relevant

101

3D reconstructionBuilding a 3D model of an object or place, its shape and often its colors, from photos, video or depth-sensor scans.
Pieter AbbeelA Belgian-American roboticist at Berkeley whose research taught robots to learn from demonstrations and from trial and error, and who co-founded the robotics company Covariant.
AI authorshipThe question of whether a work or invention produced by AI can be protected by copyright or patent, and if so who counts as its author or inventor: the AI, the person using it, or no one.
AI handsThe tendency of early AI image generators to draw hands badly — extra or missing fingers, twisted joints — which became a running joke and a quick way to spot fake images.
AI slopLow-quality content churned out in bulk by AI — bland articles, fake-looking images, filler videos — posted to grab clicks or fill space, with little care for accuracy or value.
AI watermarkingHiding an invisible signal in AI-generated text, images, audio or video so that software can later tell the content was made by AI — like a banknote's watermark, but undetectable to the eye.
AI-generated content labelingMarking text, images, audio or video as made by AI — with a visible notice, hidden data in the file, or both — so that people and platforms can tell synthetic content from real.
audio language modelAn AI language model that can take in sound, such as speech, music and everyday noises, and understand or generate it, much as text chatbots handle words.
autoencoderA neural network trained to squeeze its input into a compact code and then rebuild the original from that code. Learning to compress this way forces it to capture what matters in the data.
autoregressive modelA model that produces a sequence one piece at a time, each new piece depending on the pieces already produced — like writing a sentence word by word without going back.
Balenciaga PopeA 2023 AI-generated photo of Pope Francis in a stylish white puffer coat that fooled many viewers, becoming a landmark example of how convincing fake images had become.
Black Forest LabsA German AI company founded in 2024 by original creators of Stable Diffusion, which makes the FLUX image-generation models.
ByteDanceThe Chinese company that owns TikTok, which also runs Doubao, China's most popular AI chatbot, and builds image and video generators.
C2PAAn industry group, and the technical standard it publishes, for attaching tamper-evident records of origin and editing history to digital photos, video, audio and documents.
CLIPAn OpenAI model that learned to match pictures with their captions from hundreds of millions of web examples, so it can judge how well any piece of text describes any image.
Harold CohenA British-born painter who wrote AARON, a program that made its own drawings and paintings from the early 1970s, making him a pioneer of art produced by AI.
concept erasureRemoving a specific idea — such as a person's gender, or an artist's style — from what an AI model can represent or produce, so the model can no longer use or show it.
Content CredentialsA tamper-evident 'nutrition label' attached to a photo, video or document recording where it came from — which camera or AI tool made it and how it was edited — that anyone can inspect.
cross-attentionAttention between two different inputs: one sequence consults another, as when a translation model writing French looks back at the English sentence, or an image generator consults the text prompt.
deep synthesisThe Chinese legal term for AI that creates or alters text, images, voices, video or virtual scenes — the technology behind deepfakes — and for the rules that govern it.
deepfakeA fake but realistic video, photo or voice recording made with AI that puts words in a real person's mouth or shows them in a scene that never happened.
denoising autoencoderAn autoencoder trained to recover clean data from a deliberately damaged copy, such as an image with random pixels erased, which teaches it the structure of the data rather than how to copy.
diffusion language modelA language model that writes by starting from a fully blanked-out answer and filling it in over several rounds, settling many words at once instead of writing strictly left to right.
diffusion policyA way of training robots in which the same kind of AI that generates images instead generates the robot's next movements, letting it copy demonstrations even when there are several good ways to do a task.
digital replicaA realistic computer-made copy of a real person's voice or appearance — such as an AI clone of a singer's voice or a digital stand-in for an actor — that can say or do things the person never did.
discriminative modelA model that learns only to tell things apart — spam or not spam, cat or dog — without learning how to produce new examples of those things.
disentangled representationAn internal representation in which each part tracks one separate, meaningful factor of the data, such as one number for a face's angle, another for its lighting and another for hair color.
disinformationDeliberate falsehoods or distortions dressed up as fact, for example from a government or campaign trying to sway an election or sow distrust.
encoder–decoder architectureA two-part model design: one part, the encoder, reads the input and condenses it into an internal summary; the other, the decoder, uses that summary to produce the output.
energy-based modelA model that scores how well things fit together by giving each possibility an 'energy': low for plausible combinations, high for implausible ones, like a ball settling into the lowest valleys.
exponential moving average of weightsA smoothed copy of a model kept during training, which each update nudges only slightly toward the latest weights. The calmer copy often performs better than the jittery original.
Gaussian splattingA way of turning photos of a real place into a 3D scene made of millions of tiny, soft, colored blobs that can be viewed from any angle in real time, even on a phone or headset.
generative AIAI that produces something new on request, such as an essay, a picture, a song or a piece of code, having absorbed from enormous numbers of existing examples what such things typically look like.
generative artArt in which the artist invents a process — dice rolls, software, written instructions — and lets that process make the work; the phrase now also loosely covers pictures from AI image generators.
GhiblificationThe March 2025 craze for turning photos into pictures in the style of Japan's Studio Ghibli using ChatGPT's new image tool, and the debate it sparked over AI copying artists' styles.
GlazeA free tool that lets artists treat their pictures before posting them, with changes people barely notice, so that an AI trained to imitate their style learns a different one.
Ian GoodfellowAn American computer scientist who invented generative adversarial networks, in which two neural networks compete to produce realistic fake images, and who pioneered research on fooling AI systems.
Heart on My SleeveA 2023 song that used AI to imitate the voices of Drake and The Weeknd without their involvement; it went viral before being pulled, becoming a landmark case for AI voice cloning in music.
image captioningHaving a computer write a short description of a picture, such as 'a dog catching a frisbee in a park', to help blind people, search engines and other AI systems.
implicit neural representationA way of storing an image, shape or scene as a small neural network that, given any coordinate, returns what is there, such as a color or density, instead of as a grid of pixels.
inverse kinematicsWorking backward from where you want a robot's hand to be to the joint angles that will put it there, like working out how to bend your arm to touch your nose.
Italian brainrotA 2025 internet craze of absurd AI-generated creatures with fake-Italian names — such as a shark wearing sneakers — narrated by AI voices and hugely popular with young children.
JacobianA table listing how each output of a process responds to a small change in each input. It describes how a transformation locally stretches, squeezes and turns space.
Jensen's inequalityA rule saying that for a bowl-shaped curve, the average of the outputs is at least the output of the average. It is the hidden step behind many proofs in machine learning.
Jensen–Shannon divergenceA balanced, two-way measure of how different two sets of probabilities are, comparing each with their average. Unlike its better-known cousin, it gives the same answer in both directions.
Diederik KingmaA Dutch computer scientist who co-invented the variational autoencoder and the Adam optimizer, two of the most widely used tools for training neural networks.
Kullback–Leibler divergenceA score for the cost of believing the wrong odds: on average, how much more surprised you will be by real outcomes than someone who knew the true probabilities. It is zero only when your odds are exactly right.
LAIONA mostly volunteer group, registered as a German nonprofit, that compiled free lists of billions of online pictures and their captions. Stable Diffusion and other image generators were trained on them.
LAION-5BA free list of nearly six billion links to online images paired with their captions, released in 2022 and used to train image generators such as Stable Diffusion.
latent spaceThe hidden internal map a model builds of its data, where each item becomes a point and similar items sit near each other. Moving smoothly through it gradually changes what the model represents or generates.
liar's dividendThe advantage dishonest people gain once everyone knows fakes are easy to make: they can wave away real evidence against them by claiming it was made by AI.
Lipschitz continuityA guarantee that a function never changes too abruptly: its output can move at most a fixed multiple of how far its input moves.
Lovelace objectionThe argument, traced to Ada Lovelace in 1843, that computers cannot be truly creative because they can only do what they have been programmed to do.
Markov chain Monte CarloA family of methods for drawing random examples from a complicated probability distribution by taking a long, carefully designed random walk that eventually visits each region in proportion to its probability.
MiniMax (company)A Shanghai artificial intelligence company, founded in 2021, that makes AI companion apps, the Hailuo video generator and large language models, several released openly.
misinformationFalse or misleading information that spreads, whether or not the people sharing it know it is wrong. AI can produce it by mistake and makes it cheaper to create.
model collapseThe gradual decline of AI models trained on the output of earlier AI models: rare details vanish first, then quality and variety erode, like a photocopy of a photocopy.
multimodal AIAI that can take in or produce more than one kind of information, such as text, images, sound and video, so you can show it a photo and ask questions about it.
multimodal large language modelAn AI language model that can also take in — and sometimes produce — pictures, sound or video, so you can show it a photo or speak to it, not just type.
natural language generationGetting computers to produce human language — from turning a spreadsheet into a weather report to writing an essay or a chatbot's reply.
neural ordinary differential equationA neural network that, instead of passing data through a fixed stack of layers, describes how the data changes continuously over 'time' and uses an equation solver to follow that change.
neural radiance fieldA way of capturing a real scene from a set of photos as a small neural network that can then show the scene from any new viewpoint, as if moving a camera through it.
NightshadeA free tool for artists that subtly alters their images so that AI image generators trained on them without permission learn the wrong things — associating 'dog' with pictures of cats, say.
NO FAKES ActA proposed US law that would let people control AI-made copies of their voice and face, and would require websites to take down unauthorized fakes once notified.
non-consensual intimate imagerySexual or nude images of a real person that are shared, or made, without their consent — including fakes created with AI that show someone undressed or in sexual scenes.
normal distributionThe familiar bell-shaped curve: most values cluster near the average, and values become rapidly rarer the farther they lie from it. Measurement errors and adult heights roughly follow it.
physical AIAI built to work in the physical world rather than on a screen: the intelligence inside robots, self-driving cars, drones and other machines that must sense real surroundings and move through them.
plug and play language modelAn early way to steer what a language model writes — its topic or mood — by letting a small add-on classifier nudge the model's internal state at each word, without retraining the model.
posteriorWhat you believe after weighing new evidence against what you believed before. It is the updated belief that Bayes' theorem produces.
probability density functionA curve showing where a measurement is likely to fall. The area under the curve between two values gives the chance of landing between them.
promptThe message or instructions you give an AI system — a question, a request, some examples or a document — that it responds to. Clearer prompts generally get better results.
Alec RadfordAn American AI researcher who led OpenAI's first GPT language models and its CLIP and Whisper systems, key steps toward today's chatbots and multimodal AI.
restricted Boltzmann machineA two-layer network, one layer for the data and one hidden, that learns the patterns in data by trying to generate it. Stacks of them helped start the deep-learning revival around 2006.
right of publicityA person's legal power to decide whether businesses may use their name, face, voice or other recognizable traits to sell things, and to be paid when they do. AI's skill at copying voices and faces makes it more important.
RunwayA New York company that makes AI tools for generating and editing video, used by filmmakers and artists; it helped create the image generator Stable Diffusion.
saddle pointA spot on a surface that is a low point in one direction but a high point in another, like the middle of a horse's saddle or a mountain pass.
samplingPicking some items at random from a larger set or from a range of possibilities — surveying 1,000 voters, say, or letting an AI choose its next word by a weighted lottery.
Jascha Sohl-DicksteinAn American scientist who in 2015, with colleagues, introduced diffusion models, the technique behind most modern AI image and video generators, by borrowing ideas from physics.
source separationPulling apart a mixture of sounds into its separate parts, such as isolating one voice in a noisy party or the vocals, drums and bass in a finished song.
spatial intelligenceThe ability to understand, imagine and act in three-dimensional space and the physical world — effortless for people, and treated by many AI researchers as the next big goal after language.
Stability AIA London company that paid for and released Stable Diffusion, a free image-generating AI anyone could download, and later models for video, audio and 3D.
steeringGuiding what an AI model does — its topic, tone or behavior — while it runs, by changing its instructions, its internal signals or how its next word is chosen, rather than by retraining it.
straight-through estimatorA shortcut that lets networks learn even when they contain steps with no useful slope, such as rounding: during learning, the computer simply pretends the step passed its input straight through.
synthetic dataData created by computer programs or AI models rather than collected from the real world — such as practice math problems written by a model, or simulated street scenes for self-driving cars.
synthetic mediaImages, video, audio or text created or substantially altered by AI rather than recorded or written directly by people, whether for art, entertainment, business or deception.
SynthIDGoogle's system for hiding an invisible watermark in pictures, video, audio and text made by its AI tools, so they can later be recognized as AI-generated.
text summarizationUsing a computer to shorten a document, meeting or set of articles into a brief version that keeps the main points.
text-to-speechTechnology that reads written text aloud in a computer-generated voice, used in screen readers, voice assistants, audiobooks and navigation apps.
transformerThe design behind today's chatbots and much of modern AI. It handles text by letting every word look at every other word and decide which of them matter for understanding it.
transparency obligationsEU rules requiring that people be told when they are dealing with AI: chatbots must say they are bots, AI-made content must be marked, and deepfakes must be labeled.
transposed convolutionAn operation that roughly reverses an image network's shrinking steps, enlarging a small grid of features into a bigger one, as when a model paints a full-size image.
uncanny valleyThe eerie feeling people get from robots, dolls or computer-made faces that look almost, but not quite, human: liking grows with human likeness, then suddenly plunges.
U-NetAn image network shaped like the letter U: one half shrinks the picture to understand it, the other enlarges it back, with shortcuts between the halves so fine detail is not lost.
variational inferenceA way of approximating a hard-to-compute probability distribution by picking the closest match from a simpler family of distributions, turning a hard problem of adding up every possibility into an optimization problem.
vector quantizationCompressing data by replacing each item with the nearest entry from a small catalog of representative examples, so that only the catalog number needs to be stored or sent.
vocoderA device or program that turns a compact description of a voice back into actual sound; in modern speech AI, the final stage that produces the audio you hear.
Wasserstein distanceA way of comparing two spreads of probability by imagining one as heaps of sand that must be shoveled into the shape of the other: the less shoveling, weighted by distance, the more alike they are.
WaveNetA DeepMind model that generates speech and other sounds one tiny audio sample at a time, producing voices far more natural than earlier computer speech.
Will Smith eating spaghettiA grotesque 2023 AI-generated video of actor Will Smith eating spaghetti that became a meme and an informal yardstick: each new video model is judged by how well it redoes the scene.
world foundation modelA large AI model trained on vast amounts of video that can imagine how a scene will unfold, used to create realistic practice worlds for robots and self-driving cars.
world modelAn AI's internal simulation of how its world works, which lets it predict what will happen next — especially in response to its own actions — and so plan, imagine or practice without acting for real.