gen‑ai.news
← Back
Multimodal

Start building with Nano Banana 2 Lite and Gemini Omni Flash

Start building with Nano Banana 2 Lite and Gemini Omni Flash

Google has announced the availability of two new generative media models: Nano Banana 2 Lite, a lightweight image generation model, and Gemini Omni Flash, designed for video generation and conversational editing. The releases appear targeted at developers and builders who need capable models at lower cost and latency than flagship offerings.

Nano Banana 2 Lite sits at the efficient end of Google's image model lineup, prioritizing speed and cost over raw output quality. This kind of tiered model strategy is common across the industry - it lets developers prototype quickly, run high-volume workloads affordably, and integrate image generation into products where strict budget constraints apply. The "Lite" designation signals it is a smaller, distilled variant of a larger model in the Nano Banana 2 family.

Gemini Omni Flash extends the Gemini model family into video, offering what Google describes as high-quality video generation alongside conversational editing - a workflow where users can iteratively refine video output through natural language instructions. Conversational editing has been an active area of development across the industry, as it lowers the barrier for non-technical users to make precise adjustments without learning dedicated editing tools.

Together, these two models reflect a broader push by Google to make generative media capabilities accessible at different price and performance points. With both models now open for developer access, the near-term focus will likely be on how well Nano Banana 2 Lite holds up in real-world image quality benchmarks relative to competitors, and whether Gemini Omni Flash's conversational video editing delivers consistent, controllable results in practice.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

Suno now lets you make AI videos for your AI music
Multimodal

Suno now lets you make AI videos for your AI music

Suno has added a new "Visuals" feature that lets users generate AI video clips and images to accompany their AI-made music. Videos can automatically lipsync to song lyrics, while static images can serve as album artwork or thumbnails. The feature is available now across Suno's web, iOS, and Android apps.

Microsoft launches seven MAI models at Ignite 2026
Multimodal

Microsoft launches seven MAI models at Ignite 2026

Microsoft unveiled seven new models under its MAI lineup at Ignite 2026, spanning code generation, cybersecurity, image synthesis, real-time processing, and decision-making. The release signals a broader push by Microsoft to build out its own model portfolio alongside its existing partnership with OpenAI. Notable entries include MAI Code 2, aimed at GitHub Copilot, and MAI Image 2.7 for generative image tasks.

Building Visual Intelligence — Andreas Blattmann & Dustin Podell, Black Forest Labs
Multimodal

Building Visual Intelligence — Andreas Blattmann & Dustin Podell, Black Forest Labs

Andreas Blattmann and Dustin Podell of Black Forest Labs lay out their thinking on how generative models trained on visual data - pixels, motion, and sound - could serve as a meaningful path toward general intelligence. The conversation digs into the technical and philosophical foundations behind the lab's approach to building visual AI systems. It offers a grounded look at why the founders believe perception-driven learning is worth pursuing at the frontier.