Ho and colleagues: Imagen Video high-definition diffusion

What changed

Demonstrated text-conditional high-definition video synthesis with a cascade of video diffusion and super-resolution models.

Scientific scope

Demonstrated text-conditional high-definition video synthesis with a cascade of video diffusion and super-resolution models. Scope limitation: Imagen Video is a 2022 video-system report distinct from the earlier Imagen image generator and Meta Make-A-Video.

Evidence

The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. Imagen Video is a 2022 video-system report distinct from the earlier Imagen image generator and Meta Make-A-Video.

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.

• Ho and colleagues: Imagen Video high-definition diffusion — original paper
• Ho and colleagues: Imagen Video high-definition diffusion — official company source

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