"--- title: StreamingT2V emoji: 🔥 colorFrom: purple colorTo: blue sdk: gradio sdk_version: 4.25.0 app_file: app.py pinned: false short_description: Consistent, Dynamic, and Extendable Long Video Generation --- This repository is the official implementation of StreamingT2V. **StreamingT2V: Consistent..."
StreamingT2V is an advanced autoregressive technique that enables the creation of long videos featuring rich motion dynamics without any stagnation. It ensures temporal consistency throughout the video, aligns closely with the descriptive text, and maintains high frame-level image quality. Our demonstrations include successful examples of videos up to 1200 frames, spanning 2 minutes, and can be extended for even longer durations. Importantly, the effectiveness of StreamingT2V is not limited by the specific Text2Video model used, indicating that improvements in base models could yield even higher-quality videos.
News
* [03/21/2024] Paper StreamingT2V released!
* [04/03/2024] Code and model released!
Setup
Clone this repository and enter:
`` shell
git clone https://github.com/Picsart-AI-Research/StreamingT2V.git
cd StreamingT2V/
code
2. Install requirements using Python 3.10 and CUDA >= 11.6
StreamingT2V is an advanced autoregressive technique that enables the creation of long videos featuring rich motion dynamics without any stagnation. It ensures temporal consistency throughout the video, aligns closely with the descriptive text, and maintains high frame-level image quality. Our demonstrations include successful examples of videos up to 1200 frames, spanning 2 minutes, and can be extended for even longer durations. Importantly, the effectiveness of StreamingT2V is not limited by the specific Text2Video model used, indicating that improvements in base models could yield even higher-quality videos.
News
* [03/21/2024] Paper StreamingT2V released!
* [04/03/2024] Code and model released!
Setup
Clone this repository and enter:
`` shell
git clone https://github.com/Picsart-AI-Research/StreamingT2V.git
cd StreamingT2V/
code
2. Install requirements using Python 3.10 and CUDA >= 11.6
shell
cd StreamingT2V/
python inference.py --image=../examples/underwater.png --base_model=SVD
code
<h2 class="text-xl font-bold mt-8 mb-4 text-gray-900 dark:text-white">Results</h2>
Detailed results can be found in the Project page.
<h2 class="text-xl font-bold mt-8 mb-4 text-gray-900 dark:text-white">License</h2>
Our code is published under the CreativeML Open RAIL-M license.
We include ModelscopeT2V, AnimateDiff, DynamiCrafter in the demo for research purposes and to demonstrate the flexibility of the StreamingT2V framework to include different T2V/I2V models. For commercial usage of such components, please refer to their original license.
<h2 class="text-xl font-bold mt-8 mb-4 text-gray-900 dark:text-white">BibTeX</h2>
If you use our work in your research, please cite our publication:
@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}
}
``
