| ---
|
| license: other
|
| license_name: mit-and-apache-2.0
|
| tags: [video-frame-interpolation, slow-motion]
|
| ---
|
|
|
| # TinyPine Slow Motion
|
|
|
| The two frame-interpolation models TinyPine Studio uses for slow motion, unmodified, mirrored so the app's
|
| installer does not depend on third-party download links. TinyPine did not train or change them.
|
|
|
| | Path | Model | Author | License |
|
| |---|---|---|---|
|
| | `rife-4.25/flownet.pkl` | RIFE 4.25 | hzwer, [Practical-RIFE](https://github.com/hzwer/Practical-RIFE) | MIT (`rife-4.25/LICENSE`) |
|
| | `film/film_net_fp16.pt` | FILM, TorchScript fp16 | Google Research, [frame-interpolation](https://github.com/google-research/frame-interpolation); PyTorch export by [dajes](https://github.com/dajes/frame-interpolation-pytorch) | Apache-2.0 (`film/LICENSE`) |
|
|
|
| Practical-RIFE states that its model links are "under the same MIT license as this project".
|
| Sources: RIFE 4.25 from the Google Drive link in the Practical-RIFE README (2024-09-19); FILM from the
|
| v1.0.2 release of dajes/frame-interpolation-pytorch.
|
|
|
| SHA-256:
|
| - `rife-4.25/flownet.pkl` 6615790efd627772917205db291f51cd392528a157ecbb2ecaeec3bff8eb6de2
|
| - `film/film_net_fp16.pt` 5d48a9c8f1032f046d7dfcbed40299d51e615b4bd8bbfbb36a83c9a49c76aca9
|
|
|
