Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
move, Chat bots and Image generators: This is the era of AI video generators.
Almost every major tech company has abandoned some type of AI video model over the past couple of years, representing the next wave of generative AI technology. between Sora, Google I see 3 and Mid-flightIt quickly became a crowded market. The AI videos are a huge leap forward in the company’s creative AI offerings, and are something worth paying attention to as productive AI becomes a bigger part of the content we create and watch online. This is especially true for questions about Legitimacy The ethics of AI-generated video abound.
Don’t miss any of our unbiased technical content and lab reviews. Add CNET As Google’s preferred source.
Many of these companies also have chatbots and image generators, but I was surprised to find that there are unique differences in video generators. Some of my favorite image generator features appear in the video samples, while others are noticeably absent, e.g. Since there are so many options, I’ve rounded up all the major models you can consider, including their pricing, privacy, and my hands-on testing of each.
This is everything you need to know about AI-powered video generators. This list is updated regularly with the latest information about each generator.
What are AI video generators?
AI-based video generators are one of the latest ways technology companies are using generative AI. These programs use text-to-video and image-to-video technology that allow you to create short videos. You can enter a short description called a prompt, or upload an image to animate, and the program creates a clip created entirely using general artificial intelligence. AI-powered videos tend to be five to 10 seconds long, and some models offer synchronized audio. Because this technology is new, errors can occur – called hallucinations.
What AI video models can I use now?
Some examples of AI video generators you can use right now are: Sora by OpenAI, View 3 from Google, Adobe Firefly and Mid-flight V1. They are all paid programs that produce good results and allow you to customize the shot using control panels. Runway, an AI startup co-created Stable diffusion image generatoris another AI-powered video option with free plans. Other artificial intelligence models from LomaPika and Ideogram are also available.
Sora Join the ChatGPT family at End of 2024but it was renovated with Sora 2 in October 2025 Which made fans flock to the AI. You probably know Sora’s name from him The new social media app from OpenAI Who uses the same name. But Sora is the name of the AI-powered video archetype, and you can make videos with Sora without it Need an invitation code To use the application.
Through a web browser, Sora is a very easy to use program. It doesn’t have the same chat UI as D-E 3 –You can’t “chat” with Sora for later reviews. Instead, they are closer to traditional AI-driven creative services. In Sora, you have a panel to customize the dimensions, length, and style of your video. You can enter a prompt or upload an image for Sora to animate, and you can use some editing options to enhance your video from there. Sora’s videos are also automatically watermarked, indicating their AI origins.
Sora is only available to paying ChatGPT users. If you’re a ChatGPT Plus ($20 per month) user, you’ll get 50 priority creation points per month, with videos up to 5 seconds long at 720p. Upgrading to the Pro tier ($200 per month) gets you higher monthly credits, including 500 videos created with priority/fast creation and unlimited videos with comfort creation. Pro subscribers can also create HD videos at a maximum of 1080p, extend the duration of their videos up to 20 seconds, and have the option to download videos without the watermark.
OpenAI’s privacy policy states that it may train on your content unless you opt out. To do this in Sora, go to Settings > General, and turn it off Optimize the model for everyone. You can also exclude your videos from the general Explore feeds in Settings. (Disclosure: Ziff Davis, CNET’s parent company, in April filed a lawsuit against OpenAI, alleging that it infringed Ziff Davis’s copyrights in training and operating its AI systems.)
Google’s Veo 3 AI video generator impressed AI enthusiasts when it was publicly released at its conference I/O 2025 developer conference. In my testing I found Veo 3 to be a nice step up From my country Disappointing experience with Veo 2but the real difference is audible: Veo 3 can automatically create audio and sync it to your videos.
Veo 3 videos are eight seconds long, at 720p resolution, and are automatically generated in a 16:9 landscape format. It’s a very capable program and the videos are detailed and entertaining, but it’s not immune to all the usual AI glitches and hallucinations.
Veo 3 is available through Google’s AI Pro plan for $20 per month Filmmaker-focused streaming software. You can also take a test for Veo on YouTube. Creators can now create Wallpapers generated by artificial intelligence For their short videos, powered by Veo.
Videos automatically contain Google’s SynthID watermark Embedded (not visible in clips). Google Public Cloud Artificial intelligence policy It states that it does not exfiltrate customer data without permission.
Mid-flight It is one of the most popular AI image generators, and it has just been released The first AI video model It is called V1. You can use Midjourney to create videos between 5 and 21 seconds long at 720p resolution. You can use Midjourney via Discord or their website. Right now, video creation is paywalled for users, but it’s one of the cheaper options at $10 per month.
Mid-flight privacy policy It says it can use personal information and information included in your claims to improve its services. If you create in stealth mode, your AI images will be private; Otherwise, it will be shared in a public gallery.
I was somewhat impressed with Midjourney Value for priceHowever, you will need to be patient and specific with your claims.
Firefly A standalone AI video generator is now available to you that you can use on your computer and through Firefly Mobile app. If you’re familiar with Firefly’s AI photo tools, the video generator setup will feel familiar. The panel on the left side lets you customize your clip, and has the added benefit of letting you select the type of motion you want (zoom in and out, pan left and right, etc.). You can also select the camera angle you want, as if you wanted to simulate drone footage with an aerial view.
Some Creative Cloud plans include access to Firefly, including if you pay for one or all Adobe apps. You can check and compare options here. If you don’t have a current Adobe plan, you can try Firefly’s Standard plan ($10 per month) to create up to 20 videos per month. If you need more creation credits, the Pro plan ($30 per month) gives you up to 70 videos per month. Both Firefly plans come with unlimited Image generation with artificial intelligence. Firefly videos will be 5 seconds long and 1080p with no sound.
Adobe says videos created with Firefly are commercially safe, and its AI policy states that it won’t overlay your content. Firefly videos do not have a visible watermark, but they do have a watermark Content credentials They are automatically attached to your work. Firefly models are trained on licensed and public content.
AI enthusiasts may recognize it Runway As the startup that co-created the popular AI image generator Stable spread. You may also recognize Runway from a landmark deal it struck with a major movie studio last fall. Lionsgate It agreed to open up its catalog — thousands of hours of films like The Hunger Games and John Wick and TV shows like Mad Men — to be used to create custom AI models for the studio to use.
During my brief test of the service, I was impressed with the quick build tools and general ease of finding my way around. I have also used the service before as part of Magic Media from Canva The application is suitable if you are a fan of Canva. You can use Runway for free on its web app, with 125 points per month – you’ll use about 20 points with each generation, so it’s a pretty low limit. Upgrading ($15 per month or $144 per year) gives you 625 monthly credits, access to newer models, and the ability to upscale videos to 4K and download them without watermarks.
Runway Terms of Service It says it can train its AI on your prompts and the resulting videos but it doesn’t retain ownership of them. that it privacy policy It also states that Runway may disclose your information to affiliates, business and marketing partners. The videos you create are automatically private.
What are some other AI video projects?
Noticeably absent from this list is the Meta. The company has dedicated its resources to AI development, but does not have a publicly available AI video generator. I raised one copy in October 2024. Here’s what we know so far.
Meta Video Model for Artificial Intelligence – General movie — is just a research concept at the moment and not available to the public, with no information on when it might be.
Thanks to the search paper Meta published, we know that Movie Gen videos can be 1080p HD and up to 16 seconds long at 16 frames per second. The highlight of Movie Gen is the ability to sync audio. Movie Gen can also be used to create sound effects, ambient noise and instrumental music for up to 45 seconds, Meta said. There’s always a chance this feature won’t make it to the final release, but it will give the Meta an advantage.
Perhaps, as is the case with Google and YouTube, we will see some AI-powered features appear first on social media platforms, Instagram and Facebook. (We already have a number of other AI features Taking up space on our feeds.) Meta’s AI models for this chatbot and image generator are training On publicly available Facebook and Instagram content, as well as licensed data.
For more, see our guide to Write the best photo prompts with AI and Best AI chatbots.