|
|
--- |
|
|
pipeline_tag: text-to-video |
|
|
library_name: diffusers |
|
|
license: mit |
|
|
--- |
|
|
|
|
|
# StreamingSVD |
|
|
|
|
|
**[StreamingSVD: Consistent, Dynamic, and Extendable Image-Guided Long Video Generation](https://huggingface.co/papers/2403.14773)** |
|
|
</br> |
|
|
Roberto Henschel, Levon Khachatryan, Daniil Hayrapetyan, Hayk Poghosyan, Vahram Tadevosyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi |
|
|
</br> |
|
|
|
|
|
[Video](https://www.youtube.com/watch?v=md4lp42vOGU) | [Project page](https://streamingt2v.github.io) | [Code](https://github.com/Picsart-AI-Research/StreamingT2V) |
|
|
|
|
|
|
|
|
## 🔥 Meet StreamingSVD - A StreamingT2V Method |
|
|
|
|
|
StreamingSVD is an advanced autoregressive technique for image-to-video generation, generating long high-quality videos with rich motion dynamics, turning SVD into a long video generator. Our method ensures temporal consistency throughout the video, aligns closely to the input image, and maintains high frame-level image quality. Our demonstrations include successful examples of videos up to 200 frames, spanning 8 seconds, and can be extended for even longer durations. |
|
|
The effectiveness of the underlying autoregressive approach is not limited to the specific base model used, indicating that improvements in base models can yield even higher-quality videos. StreamingSVD is part of the StreamingT2V family. |
|
|
|
|
|
|
|
|
|
|
|
## BibTeX |
|
|
|
|
|
If you use our work in your research, please cite our publications: |
|
|
|
|
|
``` |
|
|
StreamingSVD paper coming soon. |
|
|
|
|
|
@article{henschel2024streamingt2v, |
|
|
title={StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text}, |
|
|
author={Henschel, Roberto and Khachatryan, Levon and Hayrapetyan, Daniil and Poghosyan, Hayk and Tadevosyan, Vahram and Wang, Zhangyang and Navasardyan, Shant and Shi, Humphrey}, |
|
|
journal={arXiv preprint arXiv:2403.14773}, |
|
|
year={2024} |
|
|
} |
|
|
``` |
