본문으로 건너뛰기
AI 도감

텍스트-비디오 생성

한 문장 설명으로 짧은 영상을 만든다

영상입문 #23
입력텍스트영상

이 페이지의 본문은 영어로 제공됩니다. 제목과 요약은 한국어로 번역되었습니다.

이 능력이 뜻하는 것

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.

기술적으로 구현하는 방법

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.

대표 제품

8

관련 기관

대표적 용도

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

성능을 평가하는 방법

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

경계와 난점

  • 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

뒤에 있는 개념