Gen-2
Product information, use cases, and access for Gen-2.
Pricing information
No verified public pricing is available yet.
DevPrice organizes public information and does not sell Gen-2 subscriptions. Prices and availability are determined by Gen-2.
What is Gen-2?
Gen-2 is Runway’s multimodal AI video generation model for creators and production teams who want to develop new moving images from text prompts, images, or video clips. It turns written direction and visual references into material for exploring concepts, motion, and visual style.
Users can begin with text alone, combine a driving image with a prompt, or work from an existing video clip. Its generation modes cover text and image guidance, stylization, selective edits, storyboard animation, rendering, and customization for different creative workflows.
Key features of Gen-2
Text-to-Video
Generates new videos from written prompts, allowing creators to explore visual concepts and styles without starting from filmed footage.
Image and Video Guidance
Uses an image, a combined image and text prompt, or a video clip as guidance for creating new moving-image outputs.
Stylization and Masking
Applies the style of an image or prompt across video frames, while masking enables selective treatment of specific regions.
Storyboards, Rendering, and Customization
Turns mockups into stylized animated renders, converts untextured renders into realistic outputs, and supports customization for higher-fidelity results.