BWhat changed
Transferred text-image generation to video by learning appearance from paired text-image data and motion from uncaptioned video, without paired text-video training data.
Scientific scope
Transferred text-image generation to video by learning appearance from paired text-image data and motion from uncaptioned video, without paired text-video training data. Scope limitation: The approach and outputs are scoped to the 2022 Make-A-Video study; it does not establish production-ready long-form or causally coherent video generation.
Evidence
The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. The approach and outputs are scoped to the 2022 Make-A-Video study; it does not establish production-ready long-form or causally coherent video generation.
Contributors
- The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured.
- Singer and colleagues: Make-A-Video text-to-video generation — original paper
- Singer and colleagues: Make-A-Video text-to-video generation — official research page
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction