Great creative happens when your tools move at the speed of your ideas. To help you create rich, reliable experiences while reducing regeneration time and costs, we’re adding two new models to Gemini Enterprise Agent Platform.
First, we’re announcing the general availability of Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image). This model is the fastest and most cost-efficient image generation and editing model within the Nano Banana model family. Whether you're rapid-firing ideas, A/B testing ad variations, or powering social apps for millions of users, this model gives you the power to explore, iterate, and scale with speed.
We’re also releasing Gemini Omni Flash in public preview. Grounded in Gemini's real-world knowledge, it powers high-quality video generation and conversational editing. Whether you're executing character or product swaps, performing dynamic style transfers, or adding objects and relighting scenes, this model gives you precise control to edit and refine video assets.
Both models provide some of the best price-performance among market-leading frontier models for image and video generation and editing.
Gemini Omni Flash brings conversational video generation and editing directly into your applications. Users can easily embed powerful media models into their agentic workflows to create, remix, and refine video without ever switching platforms.
We built Gemini Omni Flash with a focus across these four key areas:
Conversational editing: Swap characters, relight scenes, or alter angles using natural language while natively maintaining original audio and video tracks.
Multimodal input: Combine text, images, and video inputs to guide video generation. Gemini Omni Flash natively generates audio with every video output, while maintaining character, object, and style consistency.
World knowledge and simulation: It combines an intuitive understanding of physics with Gemini's knowledge of history, science and cultural context, bridging the gap from photorealism to meaningful storytelling.
**Text and action synchronization: **Render legible text and graphics directly into video, syncing kinetic typography and explainer text with on-screen movements.
Note: Support for audio references, video references, last frame, scene extension and higher resolutions for the Gemini Omni Flash via Gemini Enterprise Agent Platform API will be available soon.
To see the full list of model capabilities and how to integrate it check out the documentation and pricing.
“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." – Matt Chotin, Senior Director of Product, Adobe
“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.” - Nishant Tahilramani, Creative Director, Invideo
“Through our continued partnership with Google, WPP received early access to the new Gemini Omni Flash’s model and integrated it into WPP Open, our agentic marketing platform. Gemini Omni Flash’s multi-modal capabilities—allowing for 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.” – Elav Horwitz, Chief Innovation Officer, WPP
Nano Banana 2 Lite can generate an image in as little as four seconds. You can generate and iterate on design concepts in seconds, taking you from a blank page to the perfect layout instantly.
**Significant improvements over Nano Banana (Gemini 2.5 Flash Image) **
Nano Banana 2 Lite blends fast image generation with a significant leap in visual quality and capability compared to our legacy model, Nano Banana. We enhanced core capabilities so you can execute complex tasks at high speeds:
World knowledge: Quickly draft accurate contextual scenes, rough data visualizations, and location-specific mockups.
Character consistency: Maintain character identities and object fidelity across multiple swift generations to easily build out storyboarding tools or embed virtual try-ons for ecommerce.
Quick text and localization: Draft copy on the fly by rendering legible text directly into rapid generations to see how typography works across localized ad variations.
To see the full list of model capabilities and how to integrate it check out the documentation and pricing.
Note: Image generation offers the fastest latency. Image editing may experience slightly higher response time.
“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.” - Idan Yonas, Director of AI Content & Innovation, Artlist
"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." - Itay Schiff, Co-founder and Creative Director, Figma
"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." - Tao Zhang, Co-founder and Chief Product Officer, Manus AI.
C2PA content credentials and imperceptible SynthID watermarks are enabled by default to help verify content authenticity for both models.
To handle high-concurrency API requests reliably at scale, the Gemini Enterprise Agent Platform offers provisioned throughput (PT) for Nano Banana 2 Lite starting today. Provisioned throughput for Gemini Omni Flash will be rolling out soon.
Embed these image and video generation and editing capabilities into your applications and creative workflows today. Explore these resources to start building:
Try the models: Agent Studio within Gemini Enterprise Agent Platform API documentation: Nano Banana 2 Lite, Gemini Omni Flash
Access Colab notebooks: Nano Banana 2 Lite, Gemini Omni Flash
Pricing: Agent Platform Pricing for both models Prompting guides: Nano Banana, Gemini Omni Flash
Gemini Omni Flash Prompting Agent Skills