HOMIE Enables Human-Object Video Personalization

HOMIE is a multimodal framework for human-object centric video personalization, leveraging Qwen3-VL-2B and Wan2.1. It uses multimodal alignment to overcome existing limitations, effectively improving subject consistency and interaction quality in generated videos.

2026-07-21 ~ 2026-07-21 · 2 related posts

• HOMIE improves human-object video personalization with multimodal alignment — Yiyang Cai · 2026-07-21
• HOMIE pairs Qwen3-VL-2B with Wan2.1 for human-object-centric video personalization — switch2stock · 2026-07-21