Create cinematic clips, scenes, and stories with consistency using  Flow , our AI filmmaking tool. Flow was built with and for creatives and uses Google’s most capable generative models. 

Tip:To get inspired and see what Flow is capable of, visit Flow TV .

Who can use Flow

Currently, to use Flow, you must meet all of these requirements:

1. Make sure your age is verified . You must be 18 years of age or older. 
2. Be located in one of our supported regions .
3. Be subscribed to Google AI Pro, Google AI Ultra, or Google AI Ultra for Business.
   • Pro subscribers:Get access to the full Flow experience, including our powerful Veo 2 model and the latest Veo 3.1 model. If you run out of credits, purchase additional top-ups.
   • Ultra subscribers:Receive all the benefits of Pro, plus more credits and first access to our newest experimental models and advanced features like Ingredients to Video.
   • Workspace subscribers:Users on qualifying Workspace plans (Business Starter, Standard, and Plus; Enterprise Starter, Standard, and Plus; G Suite Legacy Free Edition; Education Standard, Education Plus and Google AI Pro for Education) get access at no extra charge to Flow with 100 monthly credits.
     • For our most powerful models and more credits, Google AI Ultra for Business can be added to qualifying Workspace plans to get the highest level of access to AI features and models, and access to next-generation AI tools like Whisk and Project Mariner.  Learn more about Google AI Ultra for Business.

Learn more about Google AI subscription plans .

Where you can use Flow

Learn which countries and territories support Flow .

Frequently asked questions

What browsers can I use Flow on? I’m signed up for Pro/Ultra, but I can’t access my account. How do AI Credits work? Why am I being charged credits if my generation failed? Why did I get switched to a compatible model? Will my generations contain a watermark? Why do I see "You're requesting generations too quickly"? What are the Flow user policies? What is Flow TV? How do I join the Flow community? I want more info about my data Why am I getting an "Audio Generation Failed" error?

Related resources

• Generate videos using Flow
• Learn about Flow models & supported features
• Where you can use Flow
• Report a problem or send general feedback
• Stay up-to-date with changes in Flow

Creating in Flow | How to use Google’s new AI Filmmaking Tool

Learn how to use Flow to generate videos and turn individual clips into a compelling narrative.

Generate video clips in Flow

Generate a video using “Text to Video”

Here’s how to generate a video clip based solely on a written description:

1. On your device, go to Flow .
2. Open an existing project or start a new one.
   • To open an existing project, click it.
   • To start a new project, click + New project.
3. At the bottom, in the prompt box, select Text to Video.
4. Add a text prompt that describes the scene you want to create in detail. Be specific about the subject, action, environment, lighting, and style.
   • Learn how to expand your text prompt.
5. Click Generate.
6. Flow will create a video based on your prompt.

Generate a video using "Frames to Video"

Important:Product feature availability may differ by country of use. Certain image types may not be supported.

Here’s how to generate a video that starts and/or ends with specific images you provide, create transitions, or animate a static image:

1. On your device, go to Flow .
2. Open an existing project or start a new one.
   • To open an existing project, click it.
   • To start a new project, click + New project.
3. At the bottom, in the prompt box, select Frames to Video.
4. To add your start and end frames, click Add .
   • To generate a new image, click Generate image.
     • To add an image that you want to reference, click Add  again. Then select the reference image.
   • To use an existing image, click Upload.
   • To use a saved frame, click it.
5. Add a text prompt that describes the action or transition that should happen between the frames.
   • Tip:To add a specific camera movement without describing it in your prompt, click Camera. Then select a camera move.
6. Click Generate.
7. Flow will create a video.

Generate a video using "Ingredients to Video"

Here’s how to generate a video using multiple images as references (like a character, object, and background):

1. On your device, go to Flow .
2. Open an existing project or start a new one.
   • To open an existing project, click it.
   • To start a new project, click + New project.
3. At the bottom, in the prompt box, select Ingredients to Video.
4. To add your ingredient images, click Add .
   • To generate a new image, click Generate  image.
     • To add an image that you want to reference, click Add  again. Then select the reference image.
   • To use an existing image, click Upload.
     • Tip:For the best results, provide subject or product references on a plain or segmented background.
   • To use a saved frame, click it.
5. Add a text prompt that describes how these ingredients should interact within the scene.
   • For example, with ingredients of a woman , a lava lamp , and a foggy street , you could prompt: The woman, whose torso is the lava lamp, walks down the foggy street.
6. Click Generate.
7. Flow will generate a video that combines your ingredients according to your prompt, maintaining their visual style.

Expand your text prompt in Flow

Important:This feature is only available when you use “Text to Video.”

To expand your prompts without leaving Flow, you can use predefined expanders by Flow TV or create your own.

1. On your device, open a project in Flow .
2. At the bottom, in the prompt box, select Text to Video.
3. Add a text prompt that describes the scene you want to create in detail.
4. At the bottom, click Expand.
5. Click the expander you’d like to use.
6. Review, edit, and regenerate your prompt as needed.

Create custom expanders

1. On your device, open a project in Flow .
2. At the bottom, in the prompt box, select Text to Video.
3. Click Expand> Create New Expander.
4. Fill in the name and content fields.
5. Click Save.

Delete custom expanders

1. On your device, open a project in Flow .
2. At the bottom, in the prompt box, select Text to Video.
3. Click Expand.
4. Next to the expander you want to delete, click Edit.
5. At the bottom, click Delete.

Add generated clips to a scene in Flow

To create a sequence of shots, add your generated clips to a scene:

1. On your device, go to Flow .
2. Open an existing project.
3. Hover over the clip you want to add to your sequence.
4. Click Add to scene. 

Build and refine your scene in Flow

Important:The Scenebuilder timeline currently resets when you leave your project. However, all of your individual clips are always saved in the project's clip view. A feature to save the Scenebuilder state is coming soon.

You can use Flow’s Scenebuilder to:

• Arrange multiple clips in a sequence.
• Trim the beginning and end of each clip using the handles.
• Use the Jump toand Extendfeatures to build your narrative.
• Rearrange the order of your clips.

Create your next clip using “Jump to”

Here’s how to generate a new clip that seamlessly continues an action and stays consistent with your last clip:

1. On your device, go to Flow .
2. Open an existing project.
3. Add the clip you want to continue the story from to the Scenebuilder.
4. At the top, click Scenebuilder.
5. On the timeline, click the clip you want to continue from.
6. Click Add> Jump to….
7. Add a simple text prompt.
   • For example:  She runs through the forest.

Extend an existing clip

If you need a shot to be longer, you can generate more footage and add it to the end of your original clip:

1. On your device, go to Flow .
2. Open an existing project.
3. Add the clip you want to continue the story from to the Scenebuilder.
4. At the top, click Scenebuilder.
5. On the timeline, select the clip you want to make longer.
6. Click Add> Extend….
7. Add a text prompt that describes how the action should continue.

Insert or remove an object

Here's how to seamlessly insert or remove objects in your clips:

1. On your device, go to Flow .
2. Open an existing project.
3. Hover over the clip you want to change.
4. At the top right, click Edit.
   • To insert an object, click  Insert.
   • To remove an object, click  Remove.
5. At the bottom, in the prompt box, describe the object you want to insert or remove.
   • To select where the object should appear or be removed from, draw a box on the image.
6. Click Generate.

Change a clip's camera position or motion

Here's how to reshoot a clip with a different camera position or motion:

1. On your device, go to Flow .
2. Open an existing project.
3. Hover over the clip you want to change.
4. At the top right, click Edit.
   • To change your camera position, click  Camera Position. 
   • To change your camera motion, click  Camera Motion.
5. Click the option you want.
6. Click Generate.

Achieve consistent characters and locations

• Use Ingredients to Video:This is the most reliable way to consistently use the same images for your character and key objects from one shot to the next.
• Save frame as asset:
  1. In the Scenebuilder, pause on a perfect frame of your character.
  2. Click Save frame as asset.
  3. Use this saved frame as an ingredient, start frame, or end frame for future generations.

Best practices & advanced tips when generating in Flow

Get the most out of every generation with these tips:

• Prepare clean ingredients
  • When you use “Ingredients to Video,” provide subject or product references on a plain or segmented background.
  • Make sure location and style references don't contain extra subjects, unless that is your creative intent.
• Avoid conflicting guidance
  • Your text prompt should complement, not contradict, your visual inputs.
  • Make sure your prompt references the frames or ingredients you've provided.
  • A consistent look and feel across all your ingredient images helps the model blend them more effectively.
• Iterate with Gemini
  • As a Google AI subscriber, you have access to the most capable Gemini models.
  • Visit gemini.google.com to help brainstorm. Send Gemini your prompt, an image, or even a video and ask it to write you new prompts, riff on ideas, and more.

You can create and edit images directly within your Flow projects to use as stand-alone assets or as ingredients for your videos.

Generate an image in Flow

1. On your device, go to Flow .
2. Open an existing project.
3. At the bottom, in the prompt box, select Create Image.
4. At the top right of the prompt box, select your preferred model.
5. Add a text prompt that describes the image you want to create in detail.
6. Click Generate.

Find your images in Flow

1. On your device, go to Flow .
2. Open the project your image was generated in.
3. At the top left, click Images.

Edit an image in Flow

Use the Nano Banana model to make iterative edits to your generated images:

1. On your device, go to Flow .
2. Open an existing project.
3. At the top left, click Images.
4. Hover over the image you want to change.
5. Click Edit.
6. In the prompt box, enter your desired changes.
7. Click Generate.

Use images as ingredients in Flow

You can add generated images to your prompt box and ingredients drawer:

1. On your device, go to Flow .
2. Open an existing project.
3. At the top left, click Images.
4. Hover over the image you want to use.
5. At the top left, click Add To Prompt.

Flow provides a range of features powered by various Veo models, in addition to Imagen 4 and Gemini. Different models support different features.

• Veo 2 is our default model and supports the full Flow experience. We recommend it for most uses. 
• Veo 3.1 is our newest model and will offer the best quality and experimental audio. 

Tip:Before generating, in the prompt box settings, check the active model and the latest credit costs .

Flow models & supported features

Important:If you select a feature not yet supported by Veo 3.1, Flow will notify you and automatically switch to Veo 2 to complete the request.

* Requires first frame or first and last frame** For best results, use Quality models, not fast.

Learn about experimental features

Audio Generation

Important:This is an experimental feature only available on the Veo 3.1 model.

You can now add sound effects and background noise, as well as speech in some cases.

• Add your guidance to the prompt itself. For example:
  • the sound of an ice cream truck can be heard in the background
  • the captain turns towards the ocean and says ”we set sail at daybreak!”
• Sometimes Veo can produce low-quality audio, in which case your video will not be generated. Instead, your credits will be refunded. If you get this error, you can try again or try another prompt.
• Speech generation performs better with longer text transcripts in your prompt.
• We’re working on improving the following known issues:
  • Speech is currently muted on generations depicting minors.
  • Generated speech may incorrectly trigger on-screen subtitles.

Send us your feedback on this feature so we can iterate on it.

To generate content in Flow, you need to use AI Credits. The number of credits required depends on the AI model you use. The monthly credits you receive depend on your subscription level:

• With no subscription, you receive 100 credits each month free of charge to try Flow. Users in some countries receive 180 credits each month.  Learn about monthly free-of-charge credits.
• Google AI Prosubscribers receive 1,000 AI Credits each month.
• Google AI Ultrasubscribers receive 25,000 AI Credits each month.

Check your remaining AI Credits

You'll be notified if:

• Your AI Credits are low.
• You don’t have enough AI Credits to complete a request.
• You’re out of AI Credits for the month.

To check your remaining AI Credits:

1. On your device, go to Flow .
2. At the top right, click your profile picture or initial.
3. Under your profile information, you’ll find your remaining credits. 

Check your AI Credit activity

Important:This feature is only available to Google AI Pro or Ultra subscribers.

Check your AI Credits activity

If you’re subscribed to Google AI Pro or Google AI Ultra, you can check your AI Credits activity for:

• Your remaining AI Credits.
• The next refresh date.
• Your credit usage, including the following details: 
  • Timestamp and date
  • Category (for example, Whisk, Flow)
  • Amount (shows subtractions and additions to your AI Credits)

Learn how to manage your AI Credits with Google One .

Get more AI Credits

To get more AI Credits, you can:

• Change your plan:Subscribe to a Google AI Pro or Google AI Ultra plan, or upgrade your existing plan.
  • To receive 1,000 AI Credits each month, learn how to get a Google AI Pro membership.
  • To receive 25,000 AI Credits each month, learn how to get a Google AI Ultra membership
• Buy more credits:In supported regions (except Japan), Pro and Ultra subscribers can purchase top-up credits.
• Enable credit overages:For AI Ultra for Business users only, learn how to enable credit overages.

Tip:You can share AI Credits with your Google One family group, but only the plan manager can purchase more credits or change the subscription.

About monthly free-of-charge credits

Who can receive free-of-charge credits

• All users who are not Google AI Pro or Ultra subscribers receive 100 credits per month free of charge to try Flow.
• If you’re part of a Google One family group, you’ll receive these credits if your family group plan is not a Google AI plan.

How you can use free-of-charge credits

• You can only use these credits for Veo 3.1 Fast and Veo 3.1 Quality generations.
• Access to Veo 2 models and the "Ingredients to Video" feature is not included.

How monthly credits refresh

How free-of-charge credits refresh

Your monthly free-of-charge credit refresh is triggered by your first generation.

• For example, if you use your credits for the first time on August 12, your next 100 credits will become available on September 12.
• If you don’t use the full 100 credits in a month, the unused credits don’t roll over.
• If you upgrade to a paid subscription, any remaining free-of-charge credits are immediately forfeited. They will be replaced by the new monthly credit allocation from your plan.

How Google AI subscription credits refresh

• AI Credits for your Google AI Pro or Ultra plan refresh at the start of your billing cycle.
• Unused monthly credits do not roll over to the next month.

Tip:Unlike monthly credits, top-up credits are valid for 12 months from the date of your last purchase.

Learn about credit costs per generation in Flow

Important:The AI credit costs below are per generation, not per request. Some product features will create multiple generations per request. For example, in Flow, a single request may generate 2 videos.

Tip:Limits are subject to change at any time. To find the latest costs, at the top right of your prompt box, click Settings.

We’re working to bring Flow to as many people as possible. See below for a list of supported languages, as well as countries and territories where Flow is currently available to users ages 18+.

Supported languages

• English

Supported countries & territories

Feature restrictions

Product feature availability may differ by country of use. Certain image types may not be supported.

You can provide feedback or report a problem with Flow in multiple ways. Your feedback helps us improve Flow.

Send general feedback

1. On your device, go to Flow .
2. At the top right, click More Send app feedback.
3. Enter your feedback. To help us better understand the issue, add a screenshot.
4. At the bottom, click Send.

Report offensive responses generated in Flow

1. On your device, go to Flow .
2. Open an existing project.
3. Hover over the clip you want to report.
4. At the top right, click More Flag output.
5. Select what’s wrong with the output.
6. Click Submit.

Report a legal issue

1. On your device, go to Flow .
2. At the top right, click More Report legal issue.
3. Under “Select the Google product where the content you are reporting appears,” click See more products Other.
4. Fill out the form.
5. At the bottom, click Create request.

Report an access issue

Find the latest fixes, improvements, and feature announcements to Flow below.

Updates

Flow Nov 11, 2025 update

Introducing a better way to create and edit images in Flow! 

Select “Create Image” from the prompt box to start generating images within a specific project. You can select between our Nano Banana and Imagen4 models for generating images in the prompt box. Generated images will live in the “Image” tab within a specific project, and can be edited on hover using Nano Banana. 

Images (and all iterative edits) can also be added to the ingredients drawer and used as ingredients or frames when creating other images or videos. Simply use the “Add to Prompt” button on hover of images to add it to your prompt box and ingredients drawer. 

Flow July 7, 2025 update Flow June 9, 2025 update