Skip to content

Runway gen2

Turn text, images or clips into new video

Visit official site

What Runway gen2 is

The tool is described as a multimodal AI system that generates new video from text, images or video clips, without filming new footage. The app offers several modes that turn any image, video clip or text prompt into a video work.

Generation modes

  • Text to Video synthesises video in any style from a text prompt
  • Text + Image to Video generates video from an image and a text prompt
  • Image to Video generates video from an image alone as a variation
  • Stylization applies the style of an image or prompt to every frame
  • Storyboard renders a model into a fully stylised and animated effect
  • Mask isolates a subject in a video and modifies it with a short text prompt

Inputs and structure

  • Text prompts, images and video clips are listed as inputs
  • Video to Video applies the composition and style of an image or text prompt to the structure of a source video
  • Text to Video uses text alone

Pros & cons

✓ What we like

  • Multiple modes cover text, image and clip inputs
  • Stylization applies a style to every frame

! What to watch out for

  • Each output depends on the input prompt, image or clip supplied
  • Video to Video needs an existing source video

FAQ

What inputs does it accept?

The material lists text, images and video clips as inputs.

What are the two main paths described?

Text to Video uses text alone, while Video to Video applies an image or text prompt to the structure of a source video.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review