Gemini Video Generator
Gemini Video Generator creates a video from a written description, or animates an image you already have, using Google Gemini video models. You write what you want to see, choose the format, and the component returns the video ready to keep working with it in the flow.
Use it when you need short video pieces without going through an editing studio: social media ads, product presentations or small animations from a photo.
When to use it
- Generate a short social media video from the copy of a campaign.
- Animate a product photo for an online shop page or an ad.
- Create a vertical (9:16) version of a promotional message for stories and short videos.
- Produce one video for each item of a list, for example one per catalogue product.
- Give an agent the ability to create videos when a user asks for one in a conversation.
Configuration
This component needs a credential of the Google Gemini service. See Credentials to create one.
| Field | What it does |
|---|---|
| Credential (required) | The credential of the Google Gemini service. Pick one with Choose an option or create one with Add new credential. |
| Generation Mode | How the video is created: text_to_video (from a description) or image_to_video (from an image). Default: text_to_video. |
| Video Model | The Gemini video model to use. The list is filled when you choose the credential, with the video models available to your account. |
| Aspect Ratio | Video format: 16:9 (landscape) or 9:16 (portrait). Default: 16:9. Hidden in image_to_video mode. |
| Prompt | The description of the video you want, up to 4000 characters. You can type it or connect a text from another component. In image_to_video mode, describe how the image should be animated. |
| Image File | Connection point for the starting image, in image_to_video mode. It accepts an image file or the web address (URL) of the image. |
Advanced options
| Field | What it does |
|---|---|
| Resolution | Video resolution: 720p, 1080p or 4k. Default: 720p. |
Batch processing
With the Batch Mode switch on, the component runs once for each item of the list you connect to Batch Input and returns all the results together as a list. Parallel Executions sets how many items are processed at the same time (1 to 5). Skip if Empty Batch Input skips the component when the list arrives empty, and Skip Branch if Empty Output stops the following components when the result is empty. More in Key concepts.
Using it as an agent tool
You can connect this component to an agent’s Tools input. In the Tool tab, Tool Name and Tool Description are the name and explanation the agent uses to recognise the tool and decide when to call it: write a clear description of what it does.
Output
- Video: the generated video in MP4 format, with its file name. Pass it to the next components of the flow to save it, send it or keep processing it.
- Tool: the component as a tool, to connect to an agent’s Tools input. When the agent uses it, the video is saved with the conversation and the agent receives its name and the link to watch it.
Example
The online shop Calzados Ribera wants a vertical video to present its new hiking shoe:
- Add Gemini Video Generator and choose the Google Gemini credential.
- In Video Model, pick one of the models in the list.
- Leave Generation Mode on
text_to_videoand choose9:16in Aspect Ratio. - In Prompt, write: “A green hiking shoe moving along a stone trail at sunrise, ground-level camera, fresh and bright atmosphere”.
- Run the flow and connect Video to the component that saves or publishes the file.
Good practices
- Describe the scene, the camera movement and the atmosphere in concrete sentences: the result gets closer to what you have in mind.
- To animate an image, use a sharp photo and explain in Prompt what should move.
- Try a single video first before turning on Batch Mode with a long list: each video uses your Google Gemini account.