source: google deepmind: start building with nano banana 2 lite and gemini omni flash
level: technical
google deepmind introduced nano banana 2 lite, a fast and cost-efficient image model, and gemini omni flash, a video generation and editing model. nano banana 2 lite is designed for high-throughput workflows, delivering text-to-image outputs in about 4 seconds at $0.034 per 1,000 images. it is available in google ai studio, the gemini api, and gemini enterprise agent platform, and is rolling out to consumer products like ai mode in search and the gemini app.
gemini omni flash supports video generation and conversational editing using text, image, and video inputs. it is priced at $0.10 per second of video output and currently generates up to 10-second clips. the model can combine multimodal references and apply real-world knowledge to create videos. it is available in public preview through google ai studio and the gemini api, with limitations on audio references and scene extension.
developers can chain the two models together, using nano banana 2 lite to generate images and then passing them to gemini omni flash for animation. demo apps like anywhere, space lift, and omni product studio show how to build workflows that combine rapid image creation with video editing. both models include synthid watermarking for content verification and are built on google's secure infrastructure.
why it matters: these models let developers build fast, cost-efficient multimedia pipelines that combine image and video generation for prototyping and production.
source: google deepmind: start building with nano banana 2 lite and gemini omni flash