Runway Gen-3 Can Make AI Videos of ‘Photorealistic Humans’
The race for AI video is really beginning to heat up with a slew of models suddenly being released and Runway, which has been releasing models longer than most, has just dropped its latest model Gen-3 Alpha.
Describing the model as a “new frontier for high-fidelity, controllable video generation”, Runway has shared a series of impressive videos made by its new model which are about as good as any AI video out there.
Introducing Gen-3 Alpha: Runway’s new base model for video generation.
Gen-3 Alpha can create highly detailed videos with complex scene changes, a wide range of cinematic choices, and detailed art directions.https://t.co/YQNE3eqoWf
(1/10) pic.twitter.com/VjEG2ocLZ8
— Runway (@runwayml) June 17, 2024
“Gen-3 Alpha is the first of an upcoming series of models trained by Runway on a new infrastructure built for large-scale multimodal training. It is a major improvement in fidelity, consistency, and motion over Gen-2, and a step towards building General World Models,” says Runway.
The General World Models the company speaks of is a long-term ambitious project for AI to understand the visual world and all of its dynamics so it can build an internal representation of an environment.
Gen-3 Alpha is the first of an upcoming series of models trained by Runway on a new infrastructure built for large-scale multimodal training, and represents a significant step towards our goal of building General World Models.
Prompt: Subtle reflections of a woman on the window… pic.twitter.com/Lw54twUTbs
— Runway (@runwayml) June 17, 2024
As part of the family of Gen-3 models, we have been collaborating and partnering with leading entertainment and media organizations to create custom versions of Gen-3 Alpha.
Customization of Gen-3 models allows for even more stylistically controlled and consistent characters,… pic.twitter.com/ebfyfzGoJv
— Runway (@runwayml) June 17, 2024
This leap forward in technology represents a significant milestone in our commitment to empowering artists, paving the way for the next generation of creative and artistic innovation.
Gen-3 Alpha will be available for everyone over the coming days.
Prompt: A slow cinematic push… pic.twitter.com/cLaZvGpeu6
— Runway (@runwayml) June 17, 2024
Prompt: A middle-aged sad bald man becomes happy as a wig of curly hair and sunglasses fall suddenly on his head.
(7/10) pic.twitter.com/5cVSVdc9bf
— Runway (@runwayml) June 17, 2024
What is Gen-3 Alpha?
Gen-3 Alpha is the underlying model that will power Runway’s text-to-video, image-to-video, and text-to-image tools as well as control tools like Motion Brush, Advanced Camera Controls, and Director Mode.
It was trained on videos and images by an “in-house research team that oversees all of our training” with a spokesperson adding “we use curated, internal datasets to train our models.”
Gen-3 Alpa will have a “new set of safeguards” and Content Credentials (C2PA) provenance standards.
Users will be able to customize Gen-3 models for style and consistent characters. Speaking of humans, Runway also notes that “Gen-3 Alpha excels at generating expressive human characters with a wide range of actions, gestures, and emotions, unlocking new storytelling opportunities.”
Gen-3 Alpha will be released this week and will be available to Runway subscribers, members of the Creative Partners Program, and Enterprise users.
