Gen-3 Alpha is capable of generating expressive human characters and allows for fine-grained temporal control, enabling imaginative transitions and precise key-framing. The model was developed by a cross-disciplinary team of scientists, engineers, and artists, and is designed to interpret a wide range of styles and cinematic terminology. Runway has also been partnering with leading entertainment and media organizations to create custom versions of Gen-3, allowing for more stylistically controlled and consistent characters, and meeting specific artistic and narrative requirements.
Key takeaways:
- Gen-3 Alpha is the first of a new series of models by Runway, offering improved fidelity, consistency, and motion for video generation.
- The model has been trained on videos and images and will power various tools for video and image creation, including Text to Video, Image to Video, and Text to Image tools.
- Gen-3 Alpha has been developed with new safeguards, including an improved visual moderation system and C2PA provenance standards.
- Runway is collaborating with leading entertainment and media organizations to create custom versions of Gen-3, allowing for more stylistic control and consistency, and meeting specific artistic and narrative requirements.