Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment
ComfyUI Wiki
Phantom by ByteDance Research is a subject-consistent video generation model on Wan2.1. Preserves subject identity across frames using cross-modal alignment in 14B and 1.3B.
Guides and workflows related to this model series.
No articles found.
댓글
GitHub로 로그인하고 토론에 참여하세요.