hold vs FramePack
Facts only. Adjust the shortlist without leaving this page.
| Field | H hold[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D hand-object training data. | F FramePackLong local image-to-video with a low VRAM floor. |
|---|---|---|
| Fit. | ||
| Platforms· | Linux | Linux, Windows |
| Docker | No | No |
| Commercial | yes | yes |
| Catalog. | ||
| Category | Video AI | Video AI |
| License· | MIT | Apache 2.0 |
| Language | Python | Python |
| Jobs· | video ai, 3d reconstruction, ai | image to video, local video generation, Runway alternative |
| Activity. | ||
| Stars· | 492 | 18k |
| Last commit· | Mar 10, 2026 | Aug 20, 2026 |
| Last release· | — | May 3, 2026 |
| Links | ProjectGitHubGuide | ProjectGitHubGuide |