New York-based AI startup Runway has made its latest frontier model — which creates realistic AI videos from text, image or video prompts — generally available to users willing to upgrade to a paid plan starting at $12 per month for each editor. Introduced several weeks go, Gen-3 Alpha reportedly offers significant improvements over Gen-1 and Gen-2 in areas such as speed, motion, fidelity and consistency. Runway explains it worked with a “team of research scientists, engineers and artists” to develop the upgrades but did not specify where it collected its training data. As the AI video field ramps up, current rivals include Stability AI, OpenAI, Pika and Luma Labs.

Those who are “signed up on the RunwayML platform can use the model’s high fidelity and controllable generations to power a range of creative use cases, including those for advertising — much like what OpenAI has teased with Sora,” reports VentureBeat.

Gen-3 Alpha, “trained on videos and images annotated with highly descriptive captions,” explains VB, “allows users to produce hyper-realistic video clips featuring imaginative transitions, precise key-framing of elements and expressive human characters displaying a wide range of actions, gestures and emotions.”

“Each generation produces a 10-11 second photorealistic clip with surprisingly accurate motion, including a representation of human actions that reflect the scenario and setting,” explains Tom’s Guide, following its tests of the new model.

“This is better than most AI video models,” VB notes, “but less than OpenAI’s one-minute-long generations promised with Sora (which is yet to be released).”

Tom’s Guide posted five videos based on different prompts for its testing and was particularly impressed with the motion capabilities, describing Gen-3 Alpha “as good as Sora in some tasks” and “better than Luma Labs Dream Machine at understanding motion, but without an image-to-video model it fails on consistency.”

TechRadar suggests that “Runway’s new model has to be seen to be believed,” pointing out that the company “claims to outdo any competition when it comes to handling complex transitions, as well as key-framing and human characters with expressive faces.”

While competition quickly heats up in the AI video generation space, “Runway’s release of Gen-3 Alpha is a strategic move to assert a leading position in the market,” according to TechRadar.

Related:
RunwayML Eyes $450 Million Investment, Launches Gen-3 Alpha, Forbes, 7/3/24
Runway in Talks with General Atlantic for $4 Billion Valuation Fundraise, The Information, 7/2/24
Runway’s Gen-3 Alpha Creates AI Videos Up to 10-Seconds, ETCentric, 6/16/24
Two Self-Driving Car Guys Take on OpenAI’s Sora, Kling, and Runway to Be Hollywood’s Favorite AI, Fortune, 7/8/24