Image generation

Nano Banana 2 (Gemini 3.1 Flash Image)

Name: Nano Banana 2 (Gemini 3.1 Flash Image)
Author: Google

Google's workhorse image model, model ID gemini-3.1-flash-image, described in the docs as the most versatile generalist of the Nano Banana line and the default image generator in the Gemini app.

An image model by Google · read 2026-08-14 · sourcing high

Resolution: 4K (0.5K / 1K / 2K / 4K output options)
Weights: Not released
API: Yes
Commercial use: Not established

It supports 0.5K, 1K, 2K and 4K output, up to 14 reference images, and is the only Gemini image model that accepts video as an input for video-to-image. A cheaper gemini-3.1-flash-lite-image sibling exists at 1K only.

Commercial use — Not established

The research notes for this model record other terms but do not state a commercial-use position, and no licence page was retrieved, so it is not established here. Check the vendor's own terms.

Output is watermarked. SynthID watermarking applies across the Nano Banana line

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Google's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is strong: the figures came from pages we retrieved and read. Check the vendor's current documentation

What it takes in: text, image, video
What it makes: image, text
Maximum resolution: 4K (0.5K / 1K / 2K / 4K output options)
Aspect ratios: not established
Controls: editing-by-instruction, image-to-image, reference-character-consistency, style-reference, text-rendering, inpainting, outpainting
Weights: Not released
API: Yes
Pricing: per image: $0.045 (0.5K), $0.067 (1K), $0.101 (2K), $0.151 (4K); Batch API $0.022 / $0.034 / $0.050 / $0.076
Released or updated: 2026

Supported aspect ratios is not established here. That means no page we could retrieve stated it, not that the model lacks one.

Strengths

Video-to-image input, useful for pulling stills and style from footage
Wide resolution ladder down to 0.5K for cheap iteration
Conversational, multi-turn editing in the same model

Weaknesses

4K costs more than Nano Banana Pro's 1K/2K tier, so the price ladder is non-obvious
No Search grounding on the Lite variant
Aspect-ratio support not documented per-model

Best for

Iterative editing loops and high-volume shot variations, including pulling frames and style from existing video.

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

Exact release date for gemini-3.1-flash-image was not found on a fetched Google page; third-party reporting places Nano Banana 2 as the Gemini app default from around March 2026. releasedOrUpdated is therefore year-only.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

Character and set consistency: the weakest link names “consistency”
Conditioning and control: everything you hand the model besides noise names “outpainting”
Temporal consistency: flicker, drift and morphing names “consistency”
Seeds and reproducibility: re-running a generation names “generator”

How to prompt it

Written for Nano Banana 2 (Gemini 3.1 Flash Image). See prompt craft for the full vocabulary and cinematic language for the lens, light and mood tables.

Nano Banana 2 prompt guidance
Fast everyday default for character, cartoon, stylized and reference-driven image work; edits; game sprites, tiles, backgrounds and textures; the style-key image in the explainer pipeline; marketplace cards under the hood.

Reference-driven, pass references with repeated --image. For game assets use resolution 1k, AR 1:1 for sprite/tile/texture/ui and 16:9 for backgrounds, count 1 each. Keeping one primary generator across asset kinds is itself a cohesion win.
Nano Banana 2 Lite prompt guidance
Fast reference-driven generation and edits when the brief is simple or speed/cost matters more than Pro fidelity.

Supports up to 14 image references via image_references; aspect_ratio=auto requires at least one image reference.
Gemini Omni Flash prompt guidance
Fast multimodal reference-to-video from image references and optionally one video reference; the clip generator in the explainer pipeline.

0-7 image references and 0-1 video reference (max 5 images when a video reference is present). In the explainer pipeline every call attaches the same style key via --image and runs 10s at 720p. "Never silently replace gemini_omni."

MCP servers that front Google

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

AI HomeDesign MCP Image generation
MCP server to virtually stage, redesign, enhance and declutter real-estate photos.
Adclip Image generation
Ad creative generation via MCP, copy and static images from a JSON brief. Keyless.
Aetherwave Music
Music, image, video and audio generation across top AI providers - one key, one credit pool.
ArkRoute, Visual AI API Gateway Image generation
Generate images and videos using 28+ visual AI models from OpenAI (GPT Image 2, DALL-E 3), Google (Imagen 4, Veo 3.1), ByteDance (Seedream, Seedance 2.0), and Kuaishou (K
Avocado AI Image generation
Generate AI images, videos, music, SFX & speech in any AI assistant. Results appear inline in chat.
BananaBanana Image & Video Generation Video generation
Generate images & video (Nano Banana, Veo, Omni) pay-as-you-go. No subscription, crypto payments.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Nano Banana Pro (Gemini 3 Pro Image)

Google's premium image generation and editing model, model ID gemini-3-pro-image, built on Gemini 3 Pro and announced 20 November 2025. It generates a

Image generation

Imagen 4 (Fast / Standard / Ultra)

Google's standalone dedicated text-to-image family (imagen-4.0-fast-generate-001, imagen-4.0-generate-001, imagen-4.0-ultra-generate-001), offering 1K

Image generation

Adobe Firefly Image Model 5

Adobe's current Firefly image model, announced in public beta at Adobe MAX on 28 October 2025, generating at native 4 MP resolution without an upscale

Image generation

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.