Post: Gen-2 by Runway

Gen-2 by Runway

Last Updated: July 8, 2023Categories: Video Generator1.4 min read

Runway Research has introduced Gen-2, a multi-modal AI system that can generate novel videos using text, images, or video clips. It offers various modes, including text-to-video, text + image to video, image to video, stylization, storyboard, mask, render, and customization. Gen-2 aims to revolutionize video generation by providing precise, realistic, and controllable outputs.


  • 💡 Mode 01: Text to Video – Synthesize videos in any style using a text prompt.
  • 💡 Mode 02: Text + Image to Video – Generate videos using an image and a text prompt.
  • 💡 Mode 03: Image to Video – Generate videos using only an image.
  • 💡 Mode 04: Stylization – Transfer the style of any image or prompt to every frame of a video.
  • 💡 Mode 05: Storyboard – Convert mockups into fully stylized and animated renders.
  • 💡 Mode 06: Mask – Isolate subjects in a video and modify them using text prompts.
  • 💡 Mode 07: Render – Enhance untextured renders by applying an input image or prompt.
  • 💡 Mode 08: Customization – Customize the model for higher fidelity results.


Gen-2 by Runway Research represents a significant advancement in video generation technology. Through its innovative modes, it enables users to create videos with incredible realism and control. The system’s ability to generate videos based on text, images, or video clips opens up new avenues for creativity. Gen-2’s results have been preferred over existing methods for image-to-image and video-to-video translation, demonstrating its quality and potential. Runway Research continues to lead the way in developing AI systems that empower and democratize creativity in the field of image and video synthesis.

Leave A Comment