| MAGREF: Masked Guidance for Any-Reference Video Generation | May 29, 2025 | Human-Domain Subject-to-VideoOpen-Domain Subject-to-Video | CodeCode Available | 3 |
| OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation | May 26, 2025 | Human-Domain Subject-to-VideoOpen-Domain Subject-to-Video | CodeCode Available | 4 |
| HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation | May 7, 2025 | Human-Domain Subject-to-VideoSingle-Domain Subject-to-Video | CodeCode Available | 5 |
| SkyReels-A2: Compose Anything in Video Diffusion Transformers | Apr 3, 2025 | Human-Domain Subject-to-VideoOpen-Domain Subject-to-Video | CodeCode Available | 4 |
| Concat-ID: Towards Universal Identity-Preserving Video Synthesis | Mar 18, 2025 | Human-Domain Subject-to-VideoVideo Generation | CodeCode Available | 2 |
| VACE: All-in-One Video Creation and Editing | Mar 10, 2025 | AllHuman-Domain Subject-to-Video | CodeCode Available | 7 |
| Phantom: Subject-consistent video generation via cross-modal alignment | Feb 16, 2025 | cross-modal alignmentHuman-Domain Subject-to-Video | CodeCode Available | 5 |
| Identity-Preserving Text-to-Video Generation by Frequency Decomposition | Nov 26, 2024 | Human-Domain Subject-to-VideoImage to Video Generation | CodeCode Available | 4 |
