Multimodality · 2024
HunyuanVideo: A Systematic Framework for Large Video Generative Models
A 13B open-source video foundation model with performance rivaling closed systems, the largest open video model at release and a reference architecture for open text-to-video.
Editorial record
Plain-language summary
A 13B open-source video foundation model with performance rivaling closed systems, the largest open video model at release and a reference architecture for open text-to-video.
Knowledge graph
Relationships
Descendants
Depends onEvidence: Strongly supported
Attention Is All You Need
Builds on the multimodal lineage in the archive
freshness sweep 2026
Source record
Provenance
- Record ID
- P-625
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2412.03603
- arXiv:2412.03603
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.