Multimodality · 2025

Wan: Open and Advanced Large-Scale Video Generative Models

Wan Team, Alibaba

An open-weight video foundation model suite that topped the VBench leaderboard and became a widely adopted base for the open text-to-video ecosystem.

Editorial record

Plain-language summary

An open-weight video foundation model suite that topped the VBench leaderboard and became a widely adopted base for the open text-to-video ecosystem.

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-623
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.