list
open-source
dolphin
Dolphin is a general video interaction platform based on large language models.
Video understanding: Q&A about the video.
Video processing: Basic functions such as trimming video, adding subtitles, extracting audio, and adding audio using moviepy. Video to pose/depth/canny also included.
Video generation: Text to video, pose/depth and text to video, and video pix2pix.
https://github.com/kaleido-lab/dolphin?tab=readme-ov-file
Oryx Video-ChatGPT
year 2023
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
https://github.com/mbzuai-oryx/Video-ChatGPT
demo page: https://www.ival-mbzuai.com/video-chatgpt
videochatbot
year 2023
A langchain chain is used to make a really simple chatbot. It answers your questions, and it is fed into the microsoft speecht5 TTS model. This voice is then used with wav2lip to lipsync a video, and you can profit.
https://github.com/podocarp/videochatbot/tree/master
VideoChatBot
year 2021
VideoChatBot is a library that gives python users an interaction utility that works as a videocall to a bot.