| Developers: | Stability AI |
| Date of the premiere of the system: | November 2023 |
| Branches: | Information Technology |
2023: Product Announcement
On November 21, 2023, Stability AI introduced[1] model Stable Video Diffusion based on generative artificial intelligence. This open source system allows you to create short videos based on still images or text descriptions.
Stable Video Diffusion is offered in the form of two image-to-video conversion models capable of generating 14 and 25 personnel at a configurable rate of 3 to 30 frames per second. In the future, users will be able to access the new web interface to convert text into videos. This tool can be used in many areas, including advertising, education, entertainment and other areas.
The Stable Video Diffusion source code is available in the Stability AI repository on the GitHub site, and the weights required to run the model locally are published on the Hugging Face platform. It is noted that as of November 2023, Stable Video Diffusion is not intended to create fully functional or commercial applications - you can use the model for research purposes.
Stability AI also emphasizes that Stable Video Diffusion can be adapted to various tasks, including forming materials based on a single image. The model is planned to be finalized based on the results of practical use. In the future, the solution will form the basis of a set of generative models of various purposes, around which it is planned to create a full-fledged ecosystem.
 | Stable Video Diffusion is a worthy addition to our diverse range of open source models. Our solutions cover a variety of modalities, including images, natural language, audio, 3D and program code, Stability AI said in a statement.[2] |  |
Notes
| The site content is translated by machine translation software powered by PROMT. The machine-translated articles are not always perfect and may contain errors in vocabulary, syntax or grammar. Read original article If you find inaccuracies or errors in the results of machine translation, please write to editor@tadviser.ru. We will make every effort to correct them as soon as possible. |