Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
The official implementation for "Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising".
| Date | Stars |
|---|---|
| 2026-07-24 | 308 |
| 2026-07-25 | 308 |
| 2026-07-28 | 308 |
| 2026-07-30 | 308 |
| 2026-08-06 | 308 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Gen-L-Video: Long Video Generation via Temporal Co-Denoising This repository is the official implementation of [Gen-L-Video](https://arxiv.org/abs/2305.18264). [](https://g-u-n.github.io/projects/gen-long-video/index.html) [](https://arxiv.org/abs/2305.18264) [](https://colab.research.google.com/drive/1bWROxCbt7XFHTiz5G8T4ILZBtMjtOpDn?usp=sharing) > You might be interested in [Gen-L^2](https://gen-l-2.github.io/), which works better. ## Introduction **TL;DR:** **A** <font color=#FF2000> ***universal***</font> **methodology that extends short video diffusion models for efficient** <font color=#FF2000>***multi-text conditioned long video***</font> **generation and editing.** Current methodologies for video generation and editing, while innovative, are often confined to extremely short videos (typically **less than 24 frames**) and are **limited to a single text condition**. These constraints significantly limit their applications given that real-world videos usually consist of multiple segments, each bearing different semantic information. To address this challenge, we introduce a novel paradigm dubbed as ***Gen-L-Video*** capable of extending off-the-shelf short video diffusion models for generating and editing videos comprising **hundreds of frames** with **diverse semantic segments** ***without introducing additional training, all while preserving content consistency***. <p align="center"> <img src="./statics/imgs/lvdm.png" width="1080px"/> <br> <em>Essentially, this procedure establishes an abstract long video generator and editor without necessitating any additional training, enabling the generation and editing of videos of any length using established short video generation and editing methodologies.</em> </p> ## Setup #### Clone the Repo ```shell git clone https://github.com/G-U-N/Gen-L-Video cd Gen-L-Video # The repo might be too large to clone because many long gifs are over 100 M. Fork the repo, delete the statics, and then clone it. ``` #### Install Environment via Anaconda ```shell conda env create -f requirements.yml conda activate glv conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.6 -c pytorch -c nvidia ``` ### Install [Xformers](https://github.com/facebookresearch/xformers) ```shell # (Optional) Makes the build much faster pip install ninja # Set TORCH_CUDA_ARCH_LIST if running and building on different GPU types pip install -v -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers # (this can take dozens of minutes) ``` ### Install [SAM](https://github.com/facebookresearch/segment-anything) and [Grounding DINO](https://github.com/IDEA-Research/GroundingDINO) ```SHELL pip install git+https://github.com/facebookresearch/segment-anything.git pip install git+https://github.com/IDEA-Research/GroundingDINO.git ``` or ```shell git clone https://github.com/facebookresearch/segment-anything.git cd segment-anything pip install -e . cd .. # If you have a CUDA environment, please make sure the environment variable CUDA_HOME is set. # If the cuda version of the system conflicts with the cudatoolkit version, See: https://github.com/G-U-N/Gen-L-Video/discussions/7 git clone https://github.com/IDEA-Research/GroundingDINO.git cd GroundingDINO pip install -e . ``` Note that if you are using GPU clusters that the management node has no access to GPU resources, you should submit the `pip install -e . ` to the computing node as a computing task when building the GroundingDINO. Otherwise, it will not support detection computing through GPU. #### Download Pretrained Weights Make sure git-lfs is available. See: https://github.com/git-lfs/git-lfs/blob/main/INSTALLING.md ```shell bash scripts/download_pretrained_models.sh ``` After downloa
Excerpt of 16,016 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:57a08fa7da349b20, topic:video-generation, topic:text-to-video, topic:video-editing
matched fp:57a08fa7da349b20, topic:stable-diffusion, topic:diffusion-models