This is how language models work — one token after another, each one shaped by the run of tokens already written. Applied to media, the pieces become image patches or chunks of audio, and the model builds the output in order rather than resolving all of it simultaneously.
The strength is control over sequence. Because each piece is conditioned on the actual output so far rather than on a plan, the process handles variable length naturally and can be steered mid-stream. The weakness is the other side of the same coin: errors are inherited. A drift introduced early is context for everything after it, and there is no later pass that revisits the decision.
Diffusion took the opposite bet — refine everything together, repeatedly — which is why the two families have such different failure signatures. Autoregressive output degrades along its length; diffusion output degrades in its details.
In practice
- Generation is sequential, so length and latency are closely tied.
- Errors compound forward; the model cannot go back and fix an earlier choice.
- Common in speech and language, less common in current image generation.
The mistake to avoid
Assuming every generative model works this way because chatbots do. Most image generation is not sequential at all.
Related terms
Diffusion model
A diffusion model generates by starting from random noise and removing a little of it at a time until a picture or clip is left behind.
Diffusion transformer
A diffusion transformer is a diffusion model whose internals are a transformer — the same architecture behind large language models — instead of the convolutional network earlier image models used.
Text-to-speech
Text-to-speech converts written text into spoken audio using a synthetic voice you choose before generating.
Multimodal model
A multimodal model handles more than one kind of data — text, images, audio, video — inside a single system rather than bolting separate tools together.
Flow matching
Flow matching trains a model to follow a direct path from noise to data, rather than learning to reverse a long chain of noise-adding steps.
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.