Google Cloud has made Nano Banana 2 Lite generally available and released Gemini Omni Flash in public preview on its Gemini Enterprise Agent Platform, expanding its image and video generation tools for business users.
Nano Banana 2 Lite is an image generation and editing model, while Gemini Omni Flash is built for video generation and conversational editing. Both are intended for applications and workflow tools built on Google Cloud's platform.
Nano Banana 2 Lite is the fastest and lowest-cost image model in the Nano Banana family. It can generate an image in as little as four seconds, with editing taking slightly longer.
Gemini Omni Flash is priced at USD $0.10 per second of video output. It supports conversational editing, multimodal inputs including text, images, and video, and native audio generation with video output.
Creative tools
Several software and media groups are already using or testing the models in products and internal systems. Adobe plans to bring both models to Firefly, its creative AI product.
"We're excited to bring Google's newest models, including Gemini Omni Flash and Nano Banana 2 Lite, to Adobe Firefly, our all-in-one creative AI studio, to help creators move faster from idea to finished content. These new models build on Adobe's strategy to deliver our pro-grade tools and the industry's top creative AI models in a connected workflow, giving creators flexibility and control over how they bring their creative ideas to life," said Matt Chotin, Senior Director of Product, Adobe.
Invideo highlighted the video model's production uses.
"The thing that immediately caught my attention was the sheer range of what the Gemini Omni Flash model does. The VFX capabilities surprised me, and looking at it as a producer, that brings in some very interesting possibilities. But the hybrid possibilities are what excite me most. You take the crews you have always worked with in the live-action world, and you bring the breadth of what AI can do now onto the same set," said Nishant Tahilramani, Creative Director, Invideo.
WPP said it had early access to Gemini Omni Flash and integrated it into WPP Open, its marketing platform.
"Through our continued partnership with Google, WPP received early access to the new Gemini Omni Flash model and integrated it into WPP Open, our agentic marketing platform. Gemini Omni Flash's multimodal capabilities, allowing seamless image, audio, and video input references, combined with intuitive conversational editing, represent a leap forward for controlled AI production. Teams have tested asset localization, precise product swaps, and dynamic style transfers for clients. We are thrilled to partner with Google Cloud to continually push the boundaries of AI-driven creativity and deliver highly adaptable, intelligent work for our clients," said Elav Horwitz, Chief Innovation Officer, WPP.
Speed focus
Google is positioning Nano Banana 2 Lite around speed and cost for rapid image creation, iteration, and editing. The model improves on the earlier Nano Banana version in visual quality and in tasks such as contextual scene creation, character consistency, and text rendering.
Those features are aimed at uses including design mock-ups, storyboards, virtual try-ons, localized advertising, and rough data visualizations. The model is also designed to maintain character identities and object fidelity across multiple generations.
Artlist said the faster response time changes how users work with creative tools.
"Speed is no longer a limitation. When generation is faster than imagination, creators can stay inside the idea instead of waiting on the tool. Nano Banana 2 Lite brings that feeling into the creative process, letting thoughts move into visuals almost instantly. For Artlist's users, it means less time staring at a progress bar and more time creating, iterating, personalizing, and moving at the speed of culture," said Idan Yonas, Director of AI Content & Innovation, Artlist.
Figma pointed to use in rapid design iteration on Weave, its node-based canvas.
"Nano Banana 2 Lite is fast and reliable, helping designers explore more ideas to craft unique images on Figma Weave's node-based canvas. It's ideal for rapid iteration while staying in the creative flow," said Itay Schiff, Co-founder and Creative Director, Figma.
Manus AI said it has been testing the model for real-time image generation in autonomous workflows.
"We have been testing Nano Banana 2 Lite to power real-time image generation within Manus's autonomous workflows, from slide decks to web pages. Its speed suits these scenarios well, allowing our AI agent to iterate on visuals quickly and deliver results in seconds. The image quality is also impressive, coming close to the full Nano Banana 2. We look forward to continuing our partnership and building better experiences together," said Tao Zhang, Co-founder and Chief Product Officer, Manus AI.
Governance measures
Both models include C2PA content credentials and SynthID watermarks by default to help verify the authenticity of generated content. Provisioned throughput is now available for Nano Banana 2 Lite to support high-concurrency API requests, while the same service for Gemini Omni Flash will follow later.
For video work, Gemini Omni Flash can handle tasks such as character swaps, relighting scenes, style transfers, object insertion, and synchronizing text and graphics with on-screen movement. It can also combine text, image, and video prompts while maintaining original audio and video tracks during editing.
Support for audio references, video references, last frame, scene extension, and higher resolutions for Gemini Omni Flash on the Gemini Enterprise Agent Platform API will be added later. The current release makes the model available in public preview at USD $0.10 per second of video output.