Artificial intelligence · 2023

Commercial text-to-video

Runway's Gen-2 turns text prompts into short video clips for the public.

Runway, a co-creator of Stable Diffusion, released Gen-1 (video-to-video) and in 2023 Gen-2, one of the first publicly available text-to-video models. Clips were a few seconds long, but they opened the path to Sora and Veo.

See it in the living tree Wikipedia

Arcs above join it to what it stood on, arcs below to what it led to. The bar places this stretch on the tree's whole timeline.

What it built on 1

Stable Diffusion 2022

Related measurements

The dashed line marks when it first worked.

Training compute of notable AI models Source: Epoch AI, Notable AI Models (CC BY 4.0)

ML hardware FLOP/s per dollar Source: Epoch AI, ML hardware (CC BY 4.0)