Generate videos with Agent Platform

To see an example of video generation in Agent Platform, run the "Gemini Omni 1.2 Flash Video Generation" notebook in one of the following environments:

Open in Colab | Open in Colab Enterprise | Open in Agent Platform Workbench | View on GitHub

You can use Gemini Enterprise Agent Platform to generate videos, using either Gemini Omni or Veo on Gemini Enterprise Agent Platform models in Agent Platform Media Studio or using their respective APIs.

Model versions

There are multiple video generation models that you can use. For more information, see Google models.

Key features

Gemini Omni and Veo excel at a wide range of visual and cinematic styles with the following capabilities:

• Text to video

• First frame image to video

• First and last frames to video

• Generate videos from references

• Extend videos

• Edit videos

• Upscale videos

With gemini-omni-1.2-flash, you can generate or edit videos from 3 to 15 seconds in length at 360p, 720p, 1080p, or 4K resolution, specify generation_config.seed for reproducible video outputs, and attach custom metadata labels (labels) to organize requests and track billing costs.

For more information about writing effective text prompts for video generation, see the Video generation prompt guide and Veo best practices.

Locations

For more information about where Google models are available, see Deployments and endpoints.

Responsible AI

Gemini Omni and Veo are designed with Google's AI Principles in mind. However, it's important to understand how to test and deploy Google's models safely and responsibly. For more information, see Responsible AI for Veo.