statementSaid on 2026-11-10
The model supports up to 16 input reference images and focuses on improving complex instruction understanding, multi-image reference and image detail.
A statement by post author, said on 2026-11-10. Statements are as reported by the cited publishers — not verified by DecisionGateway.
模型最多支持输入 16 张参考图,重点提升复杂指令理解、多图参考及画面细节表现。