- Meta has showcased two new generative AI projects that will allow users to create videos from text prompts and customize edits of images in-stream.
- The first project, called “Emu Video,” uses a unified architecture for video generation tasks and can respond to a variety of inputs, such as text only, image only, and both text and image.
- The second project, called “Emu Edit,” enables users to make custom edits within visuals based on conversational prompts, making it easier to edit AI visuals and create more customized variations.
Meta Showcases New Generative AI Projects for Video Creation and Image Editing
Meta has unveiled two new projects that utilize generative AI technology to facilitate video creation and image editing. The first project, called “Emu Video,” allows users to generate high-quality video clips based on text prompts. The second project, called “Emu Edit,” enables users to make specific edits within visuals through text instructions. Both projects have the potential to offer new creative opportunities for creators and brands using generative AI. Meta has not yet announced when these tools will be available in its apps.