Stability AI gets into the video-generating game

Key Points:

  • Stability AI has announced Stable Video Diffusion, an AI model that generates videos by animating existing images. It is one of the few video-generating models available in open source.
  • The model is currently in a “research preview” phase, and users must agree to certain terms of use. There are concerns about potential misuse, as previous AI research previews have been circulated on the dark web.
  • Stable Video Diffusion comes in two models: SVD and SVD-XT. Both can generate high-quality videos at different frame rates.
  • The training data for the models is not clear, and there could be potential copyright and ethical challenges around usage rights.
  • Despite limitations, Stability AI plans to expand the models and develop a “text-to-video” tool for web users. The ultimate goal is commercialization, with potential applications in advertising, education, and entertainment.
  • Stability AI has faced financial challenges, including delayed payments and threats to revoke access to compute resources. The company recently raised $25 million through a convertible note but is still seeking higher valuation.
  • The departure of the VP of audio, Ed Newton-Rex, due to a disagreement about copyright and the use of copyrighted data, has also affected Stability AI.


Stability AI has introduced Stable Video Diffusion, an AI model for video generation. While it shows promise, there are concerns about potential misuse and challenges related to copyright and ethical usage. Stability AI is navigating financial difficulties and the departure of key personnel. Nevertheless, the company remains focused on expanding its models and exploring commercial opportunities in various industries.



Prompt Engineering Guides



©2024 The Horizon