Hong Kong University of Science and Technology (HKUST) · Text-to-Video

HOMIE

Subject-driven video framework that places a specific person plus specific objects, including logos, into generated video while holding likeness and interaction intact, aligning MLLM semantic features with VAE tokens inside self-attention. Built on Wan2.1-T2V-14B with Qwen3-VL-2B-Thinking; Apache-2.0, code and weights out, but only qualitative results published.