Generative support based on artificial intelligence has been popular for the past year. It started with support for text, but has also been expanded to include image generation, audio generation, and even video.
Most recently, Stability AI announced the introduction of Stable Video Diffusion. Through it, it allows users to enter any generation command based on artificial intelligence, and the system will generate the appropriate video for it.
Stable Video Diffusion is offered in open source form and currently targets researchers first. Its use is still limited to some purposes and has not yet been offered openly to all for the time being.
Stable Video Diffusion can generate images to text with a frame rate between 14 to 25 frames. For now, the development version is still limited and cannot be controlled using text commands, and may not generate faces well.
Anyway, for those of you who are interested in research involving artificial intelligence, you can try this model through Hugging Face today.