We uphold a strict editorial policy that focuses on factual accuracy, relevance, and impartiality. Our content, created by leading industry experts, is meticulously reviewed by a team of seasoned editors to ensure compliance with the highest standards in reporting and publishing.

The AI startup Runway hones in on perfecting video generation as it releases a new AI facial expression motion capture feature.

The company introduced 'Act-One' on Tuesday (October 22) describing it as being "a new state-of-the-art tool for generating expressive character performances inside Gen-3 Alpha."

Runway is an AI startup which has headquarters in New York. It was in June of last year when it raised $141 million from the likes of Google, Nvidia, and other key players in the technology space.

Act-One can be applied to a range of reference images, with the model preserving realistic facial expressions and translating this into characters with proportions different from the original source video.

The belief is this new addition "represents a significant step forward in using generative models for expressive live action and animated content."

"The model also excels in producing cinematic and realistic outputs, and is remarkably robust across camera angles while maintaining high-fidelity face animations. This capability allows creators to develop believable characters that deliver genuine emotion and expression, enhancing the viewer's connection to the content."

Runway says the team has been exploring how Act-One can create the generation of multi-turn, expressive dialogue scenes, which has been challenging to create in the past with generative video models.

"You can now create narrative content using nothing more than a consumer grade camera and one actor reading and performing different characters from a script.

Runway bolsters safety precautions as it launches AI facial expression motion capture

While the world of AI is advancing at a rapid pace, those in the industry have been nervous about its usage. The team behind Runway says they're "committed to responsible development and deployment," so the new tool is being released with a suite of content moderation and safety precautions.

These include robust capabilities to detect and block attempts to generate content containing public figures, as well as technical measures to verify that an end user has the right to use the voice that they create using Custom Voices.

There will also be "continuous monitoring to detect and mitigate other potential misuses of our tools and platform."

Act-One will begin gradually rolling out to users from this week, before soon being available to everyone.