Seonglae ChoShares many aspects with 3D AI in terms of understanding physical laws and spatial relationships
Most video foundation models use Masked Autoencoder for self-supervised pre-training but focus on short video sequences (16/32 frames).
Video AI Usages
Video AI Services
generate high-quality videos from text or images for model training
tencent/HunyuanVideo · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
https://huggingface.co/tencent/HunyuanVideo
Why 2023 Was AI Video’s Breakout Year, and What to Expect in 2024 | Andreessen Horowitz
2023 was a breakout year for AI video. At the start of the year, no public text-to-video models existed, and there's a lot to come.
https://a16z.com/why-2023-was-ai-videos-breakout-year-and-what-to-expect-in-2024/
Video editing
Edit Video By Editing Text - a Hugging Face Space by radames
Discover amazing ML apps made by the community
https://huggingface.co/spaces/radames/edit-video-by-editing-text
Stability AI releases Stable Animation SDK, a powerful text-to-animation tool for developers — Stability AI
Stability AI has released Stable Animation SDK, a powerful tool that allows artists and developers to create stunning animations using advanced Stable Diffusion models. With the ability to create animations from prompts, source images, or source videos, users can fully utilize all the Stable Diffusi
https://stability.ai/blog/stable-animation-sdk
Animation 3D
arxiv.org
https://arxiv.org/pdf/2506.19851
Audio to Video (not making audio after video) LTX Video
Lightricks Launches Audio-to-Video Generation with Exclusive ElevenLabs Partnership | LTX Studio
Lightricks introduces audio to video generation with LTX, launching exclusively with ElevenLabs to let sound drive video from the first frame.
https://ltx.studio/blog/ltx-audio-to-video-generation-with-elevenlabs
