Meta has released Emu Video and Emu Edit for its Facebook and Instagram social media platforms, which will allow users to create artificially generated video content.
Generative artificial intelligence (AI) has previously been used to generate pictures, but video generation has proved harder for these tools. In Meta’s Emu Video white paper, it states that previous attempts to generate video content have created footage that lacks diversity and quality.
Describing the release as “AI research milestones”, Meta stated that Emu was a unified text-to-video generation tool that would bring AI-generated images to life.
Emu Edit allows users to edit generated images or videos by typing instructions on how they want the image changed.
Meta stated that this would save users time by cutting out the need for prompt engineering, which is the process of rewriting a prompt until you create a desired image. This also gives users more control over the generated content as they do not need to start afresh with each new prompt.
To train both models, Meta stated that it required ten million synthesised data samples.
How well do you really know your competitors?
Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.
Your download email will arrive shortly
Not ready to buy yet? Download a free sample
We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below formBy GlobalData
This amount of data, it stated, has allowed Emu to follow instructions with precision and create images of great visual quality.
Meta cited several use cases for the technology, including generating story stickers, gifs and animating existing static photos.
By 2030, research analyst company GlobalData predicts that the global AI market will be worth more than $900bn.