Skip to main content
Generate a video with audio from a text prompt using Google’s Gemini Omni Flash model. Optionally provide reference images and/or videos to guide or edit the result. Describe the desired length (3-10s) and aspect ratio (16:9 or 9:16) directly in the prompt.

Inputs

ParameterDescriptionData TypeRequiredRange
modelThe Gemini video model used to generate the video.MODELYes”Omni Flash”
seedSeed controls whether the node should re-run; results are non-deterministic regardless of seed (default: 42).INTYes0 to 2147483647
promptThe text prompt describing the video to generate.STRINGYesMinimum 1 character after stripping whitespace
imagesOptional reference images to guide the video generation. Maximum of 14 images total.IMAGENoMultiple images allowed (max 14)
videosOptional reference videos to guide or edit the video generation. Maximum of 3 videos, each up to 10 seconds.VIDEONoMultiple videos allowed (max 3, each max 10s)
temperatureControls randomness in generation (default: 1.0).FLOATNo0.0 to 2.0
top_pNucleus sampling parameter (default: 0.95).FLOATNo0.0 to 1.0

Outputs

Output NameDescriptionData Type
VIDEOThe generated video with audio from the Gemini model.VIDEO
STRINGAny text response from the model, such as reasoning or explanations.STRING
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): 046842b7ec736283bba355aaa038b02fcf2416020f5f7aee7b0150d2a05bcbe6