Watch Google’s eerily realistic videos created using Lumiere AI as creators warn it could be ‘misused’

"We introduce Lumiere – a text-to-video diffusion model designed for synthesizing videos that portray realistic, diverse, and coherent motion – a pivotal challenge in video synthesis," said Google researchers in a paper.

"We introduce a Space-Time U-Net architecture that generates the entire temporal duration of the video at once, through a single pass in the model," they wrote.

The system can carry out a variety of video editing tasks, such as converting still images to video.

It can also create videos in a specific style using reference images or text prompts.

Perhaps most notable, the platform can create animations by altering specific regions of an image, per the .

The researchers did not that there is some risk of abuse when it comes to the platform.

"There is a risk of misuse for creating fake or harmful content with our technology," they said.

"And we believe that it is crucial to develop and apply tools for detecting biases and malicious use cases to ensure a safe and fair use."

Lumiere is not the only AI platform that carries a risk of misuse, ChatGPT and ElevenLabs have already been abused by cybercriminals.

ChatGPT, an advanced chatbot, has been used by amateur hackers to generate malware.

Meanwhile, ElevenLabs has been used to generate deepfakes of celebrities to spread misinformation.

Deepfakes are synthetic media in which a person's face or voice used in an existing video is replaced with someone else's.

Most recently, the technology was used to create a fake voice recording of President Joe Biden.