As a one-time aspiring filmmaker, I still like to play around with video editing software. Curious about what AI video generators can do for my movie-making experimentation, I gave Google Flow a try. But can it really replace traditional filmmaking? I had to test it out.
I learned that Flow can generate videos using text prompts or uploaded images. You describe every detail about the scene, camera movements, and angles, then add sound effects, background noise, and even speech. Google’s tool then creates a video with multiple clips; select the one you like, then build, extend, and fine-tune it from there. Here’s how my experiment went, and how you can create movie magic with Flow.
What You Need to Use Flow
You can use Google Flow with either a free account or one of the paid AI subscription plans. To provide access to Flow, Google doles out a certain number of credits per day or per month:
-
Free accounts: 50 credits per day (credits refresh daily, so you don’t have more than 50 credits to use at any one time)
-
Google AI Plus: 200 credits each month.
-
Google AI Pro: 1,000 credits each month.
-
Google AI Ultra ($100): 10,000 credits each month.
-
Google AI Ultra ($200): 25,000 credits each month.
The number of credits you chew up depends on the model you select and the duration of your videos. For the model, you can choose among Omni Flash, Veo 3.1 Quality, Veo 3.1 Lite, and Veo 3.1 Fast. The Omni Flash and Veo 3.1 Quality models generate higher-quality videos but take longer to run and use up more credits. The Veo Lite and Fast models are of lower quality but don’t take as long and use fewer credits. The credit allocation per model and duration works as follows:
-
Gemini Omni Flash: 15 credits for 4 seconds, 20 credits for 6 seconds, 25 credits for 8 seconds, 30 credits for 10 seconds. 40 credits to edit an uploaded video of any length.
-
Veo 3.1 Quality: 100 credits for 8 seconds of video.
-
Veo 3.1 Lite: 10 credits (5 credits for Ultra subscribers) to create a 4-second, 6-second, or 8-second video.
-
Veo 3.1 Fast: 20 credits (10 credits for Ultra subscribers) to create a 4-second, 6-second, or 8-second video.
Omni Flash and Veo 3.1 Quality are only available to paid accounts. However, free users can use Omni Flash in YouTube through the YouTube Shorts and YouTube Create app features at no extra cost. Paid subscribers are able to choose among all four models, but should still keep track of how many credits are used for each video. I have an AI Pro subscription, so I can tap into any of the models, though I’m careful not to bump up against my monthly limit of 1,000 credits.
Google’s Veo 3 Helped Me Produce This Video
Set the Model and Number of Videos
You should be able to create your video from any desktop browser. Google recommends you use the Chromium-based Chrome or Edge, but I had no trouble using Firefox. Log in to the Flow website with your Google account, then click New project and select the Settings icon to the right of the prompt.
(Credit: PCMag / Google)
Here, you can change the number of videos generated and which model to use. If credits are at a premium, click 1x to create one video; otherwise, you can go for two. For the model, I typically use Veo Lite or Veo Fast to limit the number of credits used and then turn to a Quality model only for a video I want to publish or share. Certain models also allow you to choose the duration of the video.
(Credit: PCMag / Google)
Create a Video From a Prompt
Since I plan to describe the video using only text, I type what I want at the prompt. I’ll sometimes use an AI chatbot, such as ChatGPT or Gemini, to create a prompt for me based on details that I provide. After adding my description, I click the arrow to submit it. For this one, I submitted the following description:
Create a photorealistic and cinematic video capturing a tense, epic aerial battle high above New York City at midday. The shot is a dynamic tracking medium close-up following a determined female superhero in a sleek, dark blue and silver suit as she dodges an energy blast. Shimmering golden energy crackles around her clenched fists. Her adversary is a massive, insectoid robot with a glinting metallic carapace and multiple glowing red optical sensors, which transforms its limbs into plasma cannons. The bright, high-contrast sunlight casts sharp shadows, emphasizing the action-packed and dangerous confrontation against a backdrop of towering skyscrapers.
(Credit: PCMag / Google)
Flow then creates the number of videos I specified. I can click the video to play it. Hovering over any video displays a small toolbar in the upper right. From there, I can click the three-dot icon to download, rename, share, or delete the video. Click Done, and the video is saved to your library.
(Credit: PCMag / Google)
If you want to add music or dialogue, you’ll need to specify that in the prompt. For the music, I can just write something like “soft jazz music is playing in the background.” For the dialogue, I have to identify which character should be speaking and put the words in quotes. Here, I submitted the following prompt:
“A man and a woman are in a crowded department store. Soft jazz music is playing in the background. The man is kneeling on one knee and holding an engagement ring. He says to the woman: ‘Will you marry me?’ The woman says: ‘Sir, this is a Walmart.’”
(Credit: PCMag / Google)
Create a Video From an Image
You can also use still images to create your video, either by generating them within Flow or uploading them. To do this, New Project from the main screen, pick your model, then click the plus icon. At the media window, I clicked Upload media and picked the photo I wanted to use to create the video.
(Credit: PCMag / Google)
In this case, I chose a photo of me sitting in the captain’s chair of the Enterprise at a Star Trek set recreation. Since Flow is relying heavily on the still image, I can keep the description brief and simple. I submitted the description as follows:
A medium shot of a confident and determined male captain in his late 30s, sitting in the iconic command chair on the bridge of the Federation starship USS Enterprise. He is wearing a classic gold Star Trek captain’s uniform from the Original Series era, reminiscent of the one worn by Captain Kirk. The camera slowly pushes in on the captain’s face, capturing his focused gaze.
Based on the image and my description, Gemini created the video, which I could then play and control.
Recommended by Our Editors
(Credit: PCMag / Google)
Create a Video From a Video
You can also create a new video from a video stored in your Flow library or uploaded from your computer. I added my video by clicking the plus sign at the prompt, selecting Upload media, and then choosing the video from my PC. I next clicked on the plus sign again, selected the video, and clicked Add to prompt.
Here, I used a video of a large animated dinosaur model I had shot at a London museum. I kept the prompt simple and told Flow to create a video of a dinosaur wearing a Santa hat running rampant down a London street. In response, the AI generated a video using the dinosaur from the photo, but then expanded it to a London Street scene with Big Ben in the background.
(Credit: PCMag / Google)
Create a Character
You can also generate your own character to use in your videos. To do this, I selected Characters at the main screen. I was then able to choose one of the default characters, upload an image of a person or animal, or describe the character through text. I opted to upload an image of a goat. I was then asked to choose a name and voice for the character and describe how the character acts.
(Credit: PCMag / Google)
When I was finished creating my character, I started a new prompt, clicked the plus icon, and then chose the character from the media window. I then described the video I wanted with the description: “Professor Goat is lecturing in front of a classroom of students and is drawing a mathematical equation on a blackboard.” In response, it created a clever video with a goat man teaching math before a class of students.
(Credit: PCMag / Google)
Can Google Be Your Cinematographer?
While the videos all looked great, very cinematic, and stylish, AI is still imperfect and glitches do pop up. In my experience, Flow didn’t always follow every detail in the prompt. As one example, the mouths of characters sometimes didn’t move when speaking. With time and tweaking, I could probably fix those errors. Still, as a first attempt in each case, Flow turned out to be a fairly adept filmmaker.
About Our Expert
Lance Whitney
Contributor
Experience
I’ve been working for PCMag since early 2016 writing tutorials, how-to pieces, and other articles on consumer technology. Beyond PCMag, I’ve written news stories and tutorials for a variety of other websites and publications, including CNET, ZDNet, TechRepublic, Macworld, PC World, Time, US News & World Report, and AARP Magazine. I spent seven years writing breaking news for CNET as one of the site’s East Coast reporters. I’ve also written two books for Wiley & Sons—Windows 8: Five Minutes at a Time and Teach Yourself Visually LinkedIn.
I’ve used Windows, Office, and other Microsoft products for years so I’m well versed in that world. I also know the Mac quite well. I’m always working with iOS, iPadOS, watchOS, and Android on my various mobile devices. And these days, I write a lot about AI, so that’s become another key area for me.
My wife always jokes about all the tech products we have around the house, but I manage to put them to good use for my articles. I like Lenovo computers, so I own a couple of Lenovo desktops and several laptops. I have three MacBooks and a Mac mini. For my mobile life and work, I use an iPhone 16 Pro, iPad Pro, and iPad mini as well as an Apple Watch. But since I write about Android, I own several Android phones and tablets. Like any tech person, I have a cabinet full of cables, wires, and assorted mysterious gadgets. And when it’s time to take a break from writing, I have an old Xbox 360 and Nintendo Wii, both of which I use for exercise and fitness games.
Read Full Bio
