Product Launch · Xiaohu Explains

Google Ships Nano Banana 2 Lite and the Omni Flash Video Model: 4-Second Image Gen, the Fastest and Cheapest in the Line

Image generation in just 4 seconds at roughly $0.034 per 1K images; the Omni Flash video model opens to developers for the first time on the same day.
At a Glance
  • Google has released Nano Banana 2 Lite (model codename gemini-3.1-flash-lite-image), currently the fastest and cheapest image-generation model in the Nano Banana line: one image in 4 seconds, $0.034 per 1K images.
  • Google is opening the Gemini Omni Flash video model (gemini-omni-flash-preview) to developers for the first time, with video generation and conversational editing from mixed text, image, and video input, priced at $0.10 per second of video — the same as Veo 3.1 Fast.
  • The two models can be chained: generate an image with Nano Banana 2 Lite, then hand it to Omni Flash to turn it into a moving video, keeping session context via the Interactions API, with up to 3 rounds of edits stacked in a row.
  • Nano Banana 2 Lite is live across AI Studio, the Gemini API, and Gemini Enterprise Agent Platform, plus consumer products like Search AI Mode, the Gemini App, NotebookLM, and Google Photos.
  • Omni Flash currently generates only 10-second videos, does not yet support uploading audio references or scene extension, and character consistency across cut shots is still unstable.
A note on stance: this piece is sourced from Google's official blog — a vendor's own launch content. The latency, pricing, and capability claims are all Google's own framing, and the benchmark charts are Google's self-assessment. What follows restates the official account directly; readers can verify it themselves in AI Studio.
1Two in One Day

Google Dropped Two New Models at Once

On June 30, 2026, Google announced it was opening two new models to developers: the image-generation model Nano Banana 2 Lite, and the video generation / editing model Gemini Omni Flash.

One handles images, one handles video — and Google designed them, from the start, to plug into each other: once a still image is generated, pass it to the video model and it comes to life.
Why it's worth a look: Gemini Omni Flash is the first time a Google video model has been opened to developers via API, priced at $0.10 per second of video — on par with Veo 3.1 Fast; Nano Banana 2 Lite does text-to-image in just 4 seconds at $0.034 per 1K images, the fastest and cheapest version in the current Nano Banana line, and Google recommends swapping it straight in for the original Nano Banana.
Hero demo clip from the official launch page: a showcase of both generative-media models. Source: Google's official blog
2Official Benchmark

One Official GIF Shows Just How Much Faster and Cheaper

This official benchmark GIF puts price on the x-axis and latency on the y-axis; the further toward the lower-left Nano Banana 2 Lite sits, the faster and cheaper it is.

Image generation and editing: latency vs. price comparison GIF
Official benchmark GIF: the position of image generation and editing across the two dimensions of latency and price. Source: Google's official blog
4s
Text-to-image time; Google says it suits interactive prototyping and quick sketches
$0.034
Cost per 1K images (Google's per-1K-image figure), about ¥0.24

Google adds that although speed is the headline, Nano Banana 2 Lite still holds a usable level on prompt adherence, character consistency, and the clarity of text in images — it isn't trading quality for speed.

Official demo: on the same "animal counting" task, a speed-and-quality comparison between Nano Banana 2 Lite and the previous Nano Banana 2. Source: Google's official blog
3Family Tiers

Nano Banana Now Has Four Tiers — Which One to Use

With Lite added, Nano Banana now has four tiers. They aren't a simple high/mid/low ladder — they split by trade-offs among speed, quality, and control. Get each one's positioning clear before you pick.

TierModel CodenamePositioning
Nano Banana 2 LiteGemini 3.1 Flash Lite ImageSpeed-first. Tuned for near-real-time, high-throughput batch scenarios, with latency pushed to the minimum
Nano Banana 2Gemini 3.1 Flash ImageGeneral workhorse. High quality at lower latency, the best balance of performance and cost
Nano Banana ProGemini 3 Pro ImageProfessional, complex scenes. Strongest control and reasoning, for work where accuracy matters more than speed
Nano Banana (original)Gemini 2.5 Flash ImageThe legacy model Google flags as old; it recommends upgrading to Lite for gains in quality, speed, and cost
Comparison table of Nano Banana 2 Lite, Nano Banana 2, and Nano Banana Pro
Official model comparison table: the capability tiers of Nano Banana 2 Lite, Nano Banana 2, and Nano Banana Pro. Source: Google's official blog
Google's Own Words

Lite isn't a stripped-down version — it's Google's recommended replacement for users on the original Nano Banana. The post states plainly that "you can swap it out now for immediate benefits across key performance dimensions" — in other words, upgrading from the original to Lite is the default move Google is suggesting.

4Core Capabilities

A Video Model You Can Finally "Edit by Conversation"

Omni Flash is a model Google showed off at I/O; this is the first time it's been handed to developers via API. It wires Gemini's multimodal understanding together with video generation and editing, so it can revise video while listening to natural-language instructions. Google highlights four capabilities — let's take them one at a time.

The Key Point

You used to need two separate systems for "generate a video" and "then edit it." Omni Flash puts generation and conversational editing in one model: you give an instruction in a single sentence and it keeps revising on the already-generated clip, no need to rewrite the full prompt.

Official demo: Gemini Omni Flash in action — conversational video editing and generation driven by natural-language instructions. Source: Google's official blog
conversational video editing

After generating a video, you don't rewrite the full prompt — you just revise the already-generated clip with a single natural-language instruction.

Say only "pull the camera back a bit" and it revises accordingly, without you restating the whole request from scratch.
multimodal referencing

At generation time you can feed images, text, and video all at once as reference material, keeping character looks and scene details consistent throughout.

Give it a character image plus a text description, and it keeps the same face and same setting as far as possible across the generated video.
real-world knowledge

Omni draws on the history, biology, narrative logic, and other knowledge Gemini holds, so the on-screen content is coherent and the story hangs together.

When generating a video with a plot, it uses this common sense to organize the shots more coherently, instead of just piling up visuals.
text and action synchronization

With a simple prompt, you can map text and graphics directly onto the action's timing in the video.

Spell out which line of text a given action goes with, and the on-screen action follows the rhythm of that line.
An Analogy · Conversational Editing

It's like chatting with an editor who has already watched the footage: you say one line, they revise to match — no need to restate the request from the top each time. That's the difference between "conversational editing" and the old "rewrite the prompt for every change."

Video editing benchmark evaluation chart
Official video-editing benchmark chart (self-reported data). Source: Google's official blog
5Chaining Them

How the Two Models Connect

Google says the real payoff is chaining the two models into one pipeline: use Nano Banana 2 Lite to generate an image fast, pass that image to Omni Flash as a reference to bring it to life as video, then use the Interactions API to remember the context and keep revising conversationally.

Nano Banana 2 LiteImage in 4s
As reference imagePassed downstream
Omni FlashGenerates moving video
Interactions APIKeeps context, up to 3 rounds of edits

The key here is the multi-turn session context of the Interactions API: the model remembers which image and which video clip it generated in earlier rounds, so you can revise step by step like a chat, stacking up to 3 rounds in a row without rewriting the prompt each time.

An Analogy · Multi-Turn Context

It's like Photoshop's history: you say "add a filter to this one," and the model knows you mean the image just now — no need to point it out again. Three rounds of edits is how far back this history can reach — three steps.

Video Still image
A still image grows frame by frame along a timeline into a moving video — the "image → video" pipeline

Google Ships Three Demos You Can Play With Directly

These three demo apps are the concrete realization of that pipeline, and all can be tweaked and used right in AI Studio.

Anywhere: take a selfie or upload a photo, use Lite to "teleport" you to dozens of landmarks, then open one image and use Omni Flash to turn it into an animation of that spot. Source: Google's official blog
Space Lift: an interior-design demo — upload a room photo to auto-generate styled decor concepts, pick one, and let Omni bring the design to life with camera moves. Source: Google's official blog
Omni product studio: turn Lite's still images into e-commerce showcase videos, getting an image-to-video result from a single interaction. Source: Google's official blog
6What It Means for Developers

What This Means for People Building Products

Put those capabilities into practice, and this launch actually unlocks three kinds of scenarios.

One: image-gen cost drops to about $0.034 per 1K images (roughly ¥0.24) at 4 seconds each. Product prototypes that batch-generate images and iterate quickly can run on a much smaller budget, and the marginal cost of trial and error gets very low.

Two: video generation plus conversational editing opens directly via API for the first time. Developers no longer have to bolt together a "generation model" and an "editing tool" themselves — a single API both generates and edits.

Three: image-to-video can be called as a chain. Generate an image first, turn it into video, then keep editing for up to 3 rounds — this gives rise to interactive apps like decor makeovers, landmark tours, and e-commerce showcase videos, and Google's three demos are the templates.

7Current Limits

What It Can't Do Yet

Omni Flash is currently a public preview, and Google lists a few limits of its own. Know the boundaries before diving in — don't set your expectations too high.

  • A single video generation is capped at 10 seconds; Google says longer durations are coming soon.
  • In the Gemini API, this model does not yet support uploading audio references, nor scene extension.
  • Video references under 3 seconds fit the API schema, but the model can't handle them for now.
  • Character consistency still has limits when cutting shots or panning the camera; Google says it's improving.
By the way: watermarking and content provenance
Both models are built on Google's infrastructure, and outputs carry a SynthID watermark, so you can verify whether content is AI-generated via the Gemini App, Gemini in Chrome, or Search. This is Google's provenance mechanism, and it's separate from the capability limits above.
8The Price Math

How the New Prices Stack Up Against Peers

Let's close with the hard numbers. Nano Banana 2 Lite lands as "the fastest and cheapest in the line," and Omni Flash lands "at the same price as Veo 3.1 Fast" — these two are the sharpest pricing signals of this launch.

4s
Nano Banana 2 Lite text-to-image time
$0.034
Nano Banana 2 Lite cost per 1K images
$0.10/s
Omni Flash video output pricing
10s
Omni Flash current cap on a single video

Per-Second Video Pricing: Omni Flash on Par with Veo 3.1 Fast

Gemini Omni Flash$0.10/s
Veo 3.1 Fast$0.10/s

In other words, Google priced this first-time-open video model at exactly the same per-second rate as the existing Veo 3.1 Fast. On the image side, Nano Banana 2 Lite is the fastest, cheapest tier Google explicitly names and recommends original-Nano-Banana users swap straight in for.

It's our recommended replacement for developers currently using our first version of Nano Banana, you can swap it out now for immediate benefits across key performance dimensions. Google's official blog, 2026-06-30
Source: Google's official blog post "Start building with Nano Banana 2 Lite and Gemini Omni Flash," by Alisa Fortin, published June 30, 2026. This piece is a visual English reading of that official launch content; the latency, pricing, and capability claims and benchmark charts are all Google's official framing and self-reported data. Image and video assets are copyright Google.