Views
No views yet
| Property | Value |
|---|---|
| Parameters | 5.33M |
| Weights format | safetensors (fp32) |
| Input | Two RGB frames [N, H, W, 3] + timestep float |
| Output | Interpolated RGB frame [N, H, W, 3] |
| Normalization | [0, 1] |
| Padding | Input must be padded to multiple of 64 |
| Ensemble | Enabled by default (flip-and-average TTA) |
| Block | Scale | Channels |
|---|---|---|
| 0 | 8 | 192 |
| 1 | 4 | 128 |
| 2 | 2 | 96 |
| 3 | 1 | 64 |
1from cortex_rife import load_model, interpolate_pair
2import numpy as np
3
4model = load_model() # downloads and caches from HuggingFace
5
6# BGR uint8 frames (e.g. from cv2.imread)
7img0 = np.random.randint(0, 255, (720, 1280, 3), dtype=np.uint8)
8img1 = np.random.randint(0, 255, (720, 1280, 3), dtype=np.uint8)
9
10result = interpolate_pair(model, img0, img1, timestep=0.5)
11# result: (720, 1280, 3) uint8 BGR1@inproceedings{huang2022rife,
2 title={Real-Time Intermediate Flow Estimation for Video Frame Interpolation},
3 author={Huang, Zhewei and Zhang, Tianyuan and Heng, Wen and Shi, Boxin and Zhou, Shuchang},
4 booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
5 year={2022}
6}