---
pipeline_tag: image-to-video
library_name: diffusers
license: mit
---
# TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation
This repository contains the official model weights for **TLB-VFI**, an efficient video-based diffusion model presented in the paper [TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation](https://huggingface.co/papers/2507.04984).
- 🌐 **Project Page**: [https://zonglinl.github.io/tlbvfi_page](https://zonglinl.github.io/tlbvfi_page)
- 💻 **Code**: [https://github.com/ZonglinL/TLB-VFI](https://github.com/ZonglinL/TLB-VFI)
## Abstract
Video Frame Interpolation (VFI) aims to predict the intermediate frame $I_n$ (we use n to denote time in videos to avoid notation overload with the timestep $t$ in diffusion models) based on two consecutive neighboring frames $I_0$ and $I_1$. Recent approaches apply diffusion models (both image-based and video-based) in this task and achieve strong performance. However, image-based diffusion models are unable to extract temporal information and are relatively inefficient compared to non-diffusion methods. Video-based diffusion models can extract temporal information, but they are too large in terms of training scale, model size, and inference time. To mitigate the above issues, we propose Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation (TLB-VFI), an efficient video-based diffusion model. By extracting rich temporal information from video inputs through our proposed 3D-wavelet gating and temporal-aware autoencoder, our method achieves 20% improvement in FID on the most challenging datasets over recent SOTA of image-based diffusion models. Meanwhile, due to the existence of rich temporal information, our method achieves strong performance while having 3times fewer parameters. Such a parameter reduction results in 2.3x speed up. By incorporating optical flow guidance, our method requires 9000x less training data and achieves over 20x fewer parameters than video-based diffusion models.
## Overview
TLB-VFI leverages temporal information extraction in the pixel space (3D wavelet) and latent space (3D convolution and attention) to improve the temporal consistency of the model.
## Quantitative Results
Our method achieves state-of-the-art performance in LPIPS/FloLPIPS/FID among all recent SOTAs.
## Qualitative Results
Our method achieves the best visual quality among all recent SOTAs. For more visualizations, please refer to our [project page](https://zonglinl.github.io/tlbvfi_page).
## Usage
For detailed instructions on setup, training, and evaluation, please refer to the [official GitHub repository](https://github.com/ZonglinL/TLB-VFI).
### Inference Example
You can perform inference using the provided scripts on the GitHub repository. Please ensure you have downloaded the trained model weights.
To interpolate 7 frames in between `frame0` and `frame1`:
```bash
python interpolate.py --resume_model path_to_model_weights --frame0 path_to_the_previous_frame --frame1 path_to_the_next_frame
```
To interpolate 1 frame in between:
```bash
python interpolate_one.py --resume_model path_to_model_weights --frame0 path_to_the_previous_frame --frame1 path_to_the_next_frame
```
## Citation
If you find this repository helpful for your research, please cite the paper:
```bibtex
@article{lyu2025tlbvfitemporalawarelatentbrownian,
title={TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation},
author={Zonglin Lyu and Chen Chen},
year={2025},
eprint={2507.04984},
archivePrefix={arXiv},
primaryClass={cs.CV},
}
```
