本文へスキップ
AI図鑑

テキストから動画生成

一文の説明から短い動画を生成する

動画初級 #23
入力テキスト動画

本ページの本文は英語で提供されています。タイトルと導入は日本語化されています。

この能力とは何か

Takes a text description and outputs a video with a time dimension, where frames must stay coherent with one another. It adds a hard constraint over text-to-image: temporal consistency, so objects cannot deform or teleport between neighbouring frames. Unlike image-to-video there is no starting frame; everything is determined by the prompt.

技術的にどう実現するか

The mainstream extends diffusion from two dimensions to three: a diffusion Transformer models space–time patches jointly so attention across frames constrains motion; another line uses a latent video autoencoder with spatio-temporal attention. Variable length and resolution are managed by generating and stitching in chunks. Synchronising audio and controlling camera language are recent extensions.

代表的な製品

8

関連する組織

代表的な用途

  • Fast spots for ads and short films
  • Storyboards and animated pre-visualisation
  • Short-form social media assets
  • Shot drafts for games and virtual production

どう評価するか

FVD
Distance between generated and real video distributions; lower is better
Motion consistency
Whether position and shape stay continuous across frames
Human preference
Pairwise comparison of visual quality and prompt adherence

限界と難しさ

  • Over long windows physics and causality break: objects vanish, merge or change identity
  • Complex interactions and hand motion distort most, especially where several objects touch
  • Clip length and resolution are compute-bound; beyond tens of seconds stitching shows seams

背景にある概念