Skip to main content
Google Gemini Omni (Video) generates a video with audio from a text prompt using Google’s Gemini Omni Flash models. You can optionally attach reference images and/or videos to guide the result or to edit existing footage. Describe the desired length directly in the prompt: 3 to 10 seconds for Omni Flash and Omni Flash 1.1, 3 to 15 seconds for Omni Flash 1.2.

Inputs

Common Inputs

Omni Flash 1.2 Inputs

Omni Flash 1.1 Inputs

Omni Flash Inputs

Reference Inputs

Notes:
  • The prompt must not be empty; the node raises an error if it is.
  • The text_to_video task generates from the prompt alone — attaching images or videos raises an error.
  • The image_to_video task accepts images only (no videos) and requires exactly 1 or 2 images: the first is the starting frame and the optional second is the ending frame.
  • The edit task (all models) and the extend task (Omni Flash 1.1 and 1.2 only) require exactly one input video and keep the aspect ratio of that input video, overriding aspect_ratio.
  • At most 14 images and 3 videos can be attached. Each attached video must be 10 seconds or shorter, 15 seconds or shorter with Omni Flash 1.2, and 25 seconds or shorter for the extend task, whose result can be at most 30 seconds long.
  • Omni Flash always outputs 720p 24 FPS video with audio; resolution selection is only available with Omni Flash 1.1 and 1.2.
  • temperature and top_p controls are only available with the Omni Flash model; Omni Flash 1.1 and 1.2 use fixed generation settings.

Outputs

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 1fc6017d4d6fbce8f04b2f0ded496553074b8498e3b7342179550fc768698897