Feature availability
- This feature requires an eligible Google Workspace subscription. Learn about Gemini features and plans.
- Most AI features in Vids, such as "Help me create," read-along teleprompter, and AI voiceover, are only available in English at this time. Learn more about Vids availability.
To generate a video clip from a prompt or an image, use "Generate video" in Google Vids.
You can generate up to 10 videos per day. The daily limit resets at 12 AM PT. For Google AI Pro and Google AI Ultra with family sharing, the daily limit is shared. Limits are subject to change. Generated videos are 8 seconds long with:
- 24fps frame rate
- 720p resolution
- Aspect ratio:
- Landscape (Widescreen): 16:9
- Portrait (Vertical): 9:16
Generate a video clip with AI
Important: Generated video clips are only available in landscape or portrait orientation.
- On your computer, open Google Vids.
- In the start menu, select the aspect ratio of your Vid: Landscape or Portrait
Veo 3.1.
- Or, you can:
- Select an existing Vid.
- On the right, click Veo
.
- Or, you can:
- On the side panel, in the dropdown, select Create from Scratch.
- Enter a text prompt. Include details such as the subject, location, action, camera, lighting, dialogue, sounds, and tone. For example:
- "A cat walking down a fashion week catwalk wearing designer clothes with electronic music in the background."
- "A dog driving a race car in Italy at sunset with loud engine roars."
- Optional: By default, the generated video clip’s aspect ratio matches your Vid canvas. If you want the video clip to have a different aspect ratio than your canvas, at the bottom of the prompt window, select an aspect ratio.
- Click Generate.
- Optional: To make changes to your video clip, edit your text prompt.
- To add the video clip to your Vid, hover over the generated video and click Insert
.
- Optional: You can control the video clip timeline from its own track at the bottom of your Vid.
Animate an image into a video clip with AI
Important: Generated video clips are only available in landscape or portrait orientation.
You can animate an uploaded .jpg or .png format image into an 8-second clip. To get the best result, you can:
- Use one of these supported aspect ratios:
- Landscape: 16:9
- Portrait: 9:16
- Use a high-quality source image. A sharp, clear image gives a more coherent result.
- The quality, composition, and style of your uploaded image sets the visual direction of the video.
- Enter a clear and detailed text prompt for motion.
- Instead of re-describing the scene, your text prompt should describe how the elements move or how the camera moves through the scene. Redundant description confuses the AI model.
Tip: If you upload an image with a different ratio, Vids automatically adds black bars to the video clip to fit the nearest supported aspect ratio.
- On your computer, open Google Vids.
- To start a new video, click
Start a new video.
- In the start menu, select the aspect ratio of your Vid: Landscape or Portrait
Veo 3.1.
- On the side panel, in the dropdown, select Animate an image.
- Optional: By default, the generated video clip’s aspect ratio matches your Vid canvas. If you want the video clip to have a different aspect ratio than your canvas, at the bottom of the prompt window, select an aspect ratio.
- Click Add image
.
- Select an image.
- Add a description. Describe in text how you want to animate the image into a video. Include details of how the subject should move, speak or sound. For example:
- From the image of an elephant: "The elephant moves around naturally."
- Click Create. When your video clip is ready, it shows up in the "Generate video" panel.
- Optional: To make changes to your video clip, click Edit prompt
.
- To add the video clip to your Vid, hover over the generated video and click Insert
.
- Optional: You can control the video clip timeline from its own track at the bottom of your Vid.
Generate a video clip with reference images as ingredients
Important: Videos with ingredients can only use Landscape (16:9) aspect ratio.
When you add up to 3 reference images as ingredients, you can generate video clips based on the subjects, styles, and locations captured in the images. For example, you can provide images of a woman, a yellow mug, and an office. Then you can provide this description: “Create a video of a woman drinking coffee from this mug, in this office.” If you need multiple video clips, you can re-use references to achieve consistent characters, design, and objects across multiple clips when you use the same references.
To use this new feature:
- On your computer, open Google Vids.
- In the start menu, select the aspect ratio of your Vid: Landscape or Portrait
Veo 3.1.
- Or, you can:
- Select an existing Vid.
- On the right, click Veo
.
- Or, you can:
- On the side panel, in the dropdown, select Create from scratch.
- Click Add ingredients
.
- Select up to 3 images as references.
- Enter a prompt that describes how you’d like to incorporate your ingredients by referring to the objects, styles, or people.
- Click Generate.
To get the best results generating video clips:
- Include the subject and tone.
- Use a prompt that's clear and precise.
- Include rich descriptions and cinematic language. Instead of "A car on a road," try: "Wide shot, eye-level, static camera focused on a red race convertible driving along with the camera down the center of an empty, paved road at dusk. The sky is a gradient from deep twilight blue overhead to warm orange and pink hues near the horizon. The car's red tail lights are illuminated."
- Refine your prompt until you reach your desired result.
- Review your session history. You can find the history of your generated prompts and videos from the current session. This allows you to compare, refine, and reuse your creations easily.
Tip: When you close the Vids tab, the history disappears.
Use policies for Veo
The Veo video clips are created through generative AI. Usage of this feature is subject to the Generative AI Prohibited Use Policy.
Give feedback about AI video generation
Google Workspace with Gemini is constantly learning and may not be able to support your request.
If you get a suggestion that's inaccurate or that you feel is unsafe, you can submit a feedback to let us know. Your feedback can help improve AI-assisted Workspace features and broader Google efforts in AI.
Because feedback may be human readable, do not submit data that contains personal, confidential, or sensitive information.
Give feedback on this feature
To provide general feedback on this feature, at the top, click Help Help Vids improve.
To report a legal issue, create a request.
Learn about Gemini feature suggestions
- Gemini feature suggestions don't represent Google's views, and shouldn't be attributed to Google.
- Do not rely on Gemini features as medical, legal, financial, or other professional advice.
- Gemini features may suggest inaccurate or inappropriate information. Your feedback makes Gemini more helpful and safe.
- Enterprise end users can submit feedback about their experience using this feature. End users are informed before they submit feedback that the feedback data shouldn’t contain personal, sensitive, or confidential information.
- Generated images and videos are for use only within Vids.
- Gemini generated images and videos are designed to bring your imagination to life in Vids, and may not represent real-world situations.