Sign inSign in
ConceptAI & ML

Autoregressive text-to-image modeling

Autoregressive text-to-image modeling uses GPT architecture to generate text-to-image sequences by treating image tokens as discrete multinomial distributions.
as Ming Ding defines itStanford University
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

GPT architecture1Image tokenizers1Multinomial distribution1

Lecturers

1

    Connections

    2

    The lectures that define it or assume it, and the concepts next to it.

    1 lecturer. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.