Google on Tuesday released Nano Banana 2 Lite, the latest version of its in-house AI video and image generator. The company claims that this version is significantly faster and more affordable than previous releases.
Google says this model has much lower latency and can generate images in 4 seconds, making it a good choice if you need to workshop images and generate large numbers of images in quick succession. At a cost of $0.034 per 1,000 images, it’s very affordable for those who want to draft large pieces of content or finalize it.
This release follows the launch of the original Nano Banana with Gemini 3.1 Flash last summer and Nano Banana 2 released in February. The latter introduced new features to the generator, including the ability to create more realistic images. The company also offers the Nano Banana Pro, which is described as a more powerful (and more expensive) model for advanced use cases.
While Nano Banana 2 is being called a “generalist workhorse,” Google claims that Banana 2 Lite is optimized for high-volume workflows that need to be executed rapidly.
Despite consumer backlash against so-called AI slop created by image models, companies continue to invest heavily in AI tools that can generate images and videos. However, Google often sells its models as useful tools to help create ads.
That said, Hollywood’s relationship with AI companies continues to grow closer, much to the consternation of some creative communities and audiences. In fact, Google just signed a $75 million deal with popular indie studio A24, a partnership that has come under heavy criticism from fans.
Nano Banana 2 Lite is now available through Google AI Studio and Gemini API, and Google’s Gemini Enterprise Agent Platform. Google says this will serve as a replacement for Nano Banana, which the company currently calls its “legacy model.”
Also on Tuesday, Google announced the wide release of Gemini Omni Flash, which was first introduced at Google I/O earlier this year. Flash video output costs $0.10 per second. Additionally, Google showed off a new demo app, Omni Product Studio. It says it can take still images generated by Omni and turn them into “cinematic e-commerce videos.”
“Building with generative media often requires creative iteration,” the company said in a blog post. “These two models allow developers to build comprehensive end-to-end multimedia experiences that marry rapid image generation with video creation and editing.”
If you buy through links in our articles, we may earn a small commission. This does not affect editorial independence.
