Google

Nano Banana 2

Name: Nano Banana 2
Brand: Google
Price: 0.0225 USD
Availability: InStock

AI Image Editing Model

Image Featured #2 Image-to-Image #1 Text-to-Image

Gemini 3.1 Flash with image generation capabilities. High-efficiency image generation model with support for text rendering, reference images, search grounding, and thinking mode. The efficient counterpart to Gemini 3 Pro Image.

Try Model Benchmark examples

1.0M

Context Window

Supported Modes

Text to Image Image Edit

Active

Capabilities

Function calling Structured output Batch Streaming System prompt Tool use Grounding Thinking Code execution Json mode

Details

Model ID

gemini-3.1-flash-image-preview

Also known as: gemini-3.1-flash-image

Creator

Google

Family

gemini-3.1-flash

Released

February 2026

Max Input Images

Max Output Tokens

65,536

Ready to integrate?

Access gemini-3.1-flash-image-preview via our unified API.

Create Account

Available at 4 providers

Starting from

$0.045 /image via Gemini API, Vertex AI · +2 more

Batch from $0.022/image via Gemini API, Vertex AI

Popular formats

0.5K (512×512)

~$0.050

2K (2048×2048)

~$0.106

4K (4096×4096)

~$0.153

Prices shown are in USD

See all providers

Provider Performance

Fastest generation through gemini at 25,839ms median latency with 73.7% success rate.

Aggregated from real API requests over the last 30 days.

Generation Time

gemini

p95: 42,574ms

replicate

p95: 51,892ms

vertex

p95: 105,302ms

fal

p95: 102,396ms

Success Rate

gemini

73.7%

1,078 / 1,463 requests

replicate

40.9%

113 / 276 requests

vertex

35.8%

228 / 637 requests

fal

86.5%

328 / 379 requests

Time to First Byte

gemini

24,248ms

p95: 38,742ms

replicate

30,023ms

p95: 51,354ms

vertex

43,959ms

p95: 104,067ms

fal

48,155ms

p95: 102,652ms

Provider Rankings

#	Provider	p50 Gen Time	p95 Gen Time	Success Rate	TTFB (p50)
1	gemini	25,839ms	42,574ms	73.7%	24,248ms
2	replicate	30,023ms	51,892ms	40.9%	30,023ms
3	vertex	45,061ms	105,302ms	35.8%	43,959ms
4	fal	48,044ms	102,396ms	86.5%	48,155ms

Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.

Providers & Pricing (5)

Nano Banana 2 is available from 5 providers, with per-image pricing starting at $0.0225 through fal.ai.

fal.ai

Text to Image

fal/gemini-3.1-flash-image-preview

Provider Model ID: fal-ai/nano-banana-2

Output

Image 0.5K

$0.060 per image

Image 1K

$0.080 per image

Image 2K

$0.120 per image

Image 4K

$0.160 per image

Pricing Notes (5)

• $0.08 per image at 1K (standard rate)
• 0.5K outputs charged at 0.75x ($0.06)
• 2K outputs charged at 1.5x ($0.12)
• 4K outputs charged at 2x ($0.16)
• Web search adds $0.015 per request

View official pricing • As of Feb 26, 2026

fal.ai

Image Edit

fal/gemini-3.1-flash-image-preview-edit

Provider Model ID: fal-ai/nano-banana-2/edit

Output

Image 0.5K

$0.060 per image

Image 1K

$0.080 per image

Image 2K

$0.120 per image

Image 4K

$0.160 per image

Pricing Notes (5)

• $0.08 per image at 1K (standard rate)
• 0.5K outputs charged at 0.75x ($0.06)
• 2K outputs charged at 1.5x ($0.12)
• 4K outputs charged at 2x ($0.16)
• Web search adds $0.015 per request

View official pricing • As of Feb 26, 2026

Replicate

Text to Image Image Edit

replicate/gemini-3.1-flash-image-preview

Provider Model ID: google/nano-banana-2

Output

Image 1K

$0.067 per image

Image 2K

$0.101 per image

Image 4K

$0.151 per image

Pricing Notes (3)

• $0.067 per output image at 1K
• $0.101 per output image at 2K
• $0.151 per output image at 4K

View official pricing • As of Feb 26, 2026

Gemini API

Text to Image Image Edit

gemini/gemini-3.1-flash-image-preview

Provider Model ID: gemini-3.1-flash-image-preview

Input

Token

$0.250 per 1M

Output

Token text

$1.50 per 1M

Image 0.5K

$0.045 per image

Image 1K

$0.067 per image

Image 2K

$0.101 per image

Image 4K

$0.151 per image

Pricing Notes (4)

• $0.045 per output image at 512px (0.5K) (747 tokens)
• $0.067 per output image at 1024x1024px (1K) (1120 tokens)
• $0.101 per output image at 2048x2048px (2K) (1680 tokens)
• $0.151 per output image at 4096x4096px (4K) (2520 tokens)

View official pricing • As of Feb 26, 2026

Vertex AI

Text to Image Image Edit

vertex/gemini-3.1-flash-image-preview

Provider Model ID: gemini-3.1-flash-image-preview

Input

Token

$0.250 per 1M

Output

Token text

$1.50 per 1M

Image 0.5K

$0.045 per image

Image 1K

$0.067 per image

Image 2K

$0.101 per image

Image 4K

$0.151 per image

Pricing Notes (4)

• $0.045 per output image at 512px (0.5K) (747 tokens)
• $0.067 per output image at 1024x1024px (1K) (1120 tokens)
• $0.101 per output image at 2048x2048px (2K) (1680 tokens)
• $0.151 per output image at 4096x4096px (4K) (2520 tokens)

View official pricing • As of Feb 26, 2026

gemini-3.1-flash-image API OpenAI-compatible

Connect to Nano Banana 2 via the Lumenfall OpenAI-compatible API to integrate high-speed text-to-image generation and image editing into your workflow. The unified endpoint allows for programmatic creation of visual assets and precise modifications to existing images through a single interface.

Base URL

https://api.lumenfall.ai/openai/v1

Model

gemini-3.1-flash-image-preview

Code Examples

Text to Image

/v1/images/generations

curl -X POST \

  https://api.lumenfall.ai/openai/v1/images/generations \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "gemini-3.1-flash-image-preview",

    "prompt": "",

    "size": "1024x1024"

}'

# Response:

# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

import OpenAI from 'openai';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

  baseURL: 'https://api.lumenfall.ai/openai/v1'

});

const response = await client.images.generate({

  model: 'gemini-3.1-flash-image-preview',

  prompt: '',

  size: '1024x1024'

});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

console.log(response.data[0].url);

from openai import OpenAI

client = OpenAI(

    api_key="YOUR_API_KEY",

    base_url="https://api.lumenfall.ai/openai/v1"

response = client.images.generate(

    model="gemini-3.1-flash-image-preview",

    prompt="",

    size="1024x1024"

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

print(response.data[0].url)

Image Edit

/v1/images/edits

curl -X POST \

  https://api.lumenfall.ai/openai/v1/images/edits \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -F "model=gemini-3.1-flash-image-preview" \

  -F "[email protected]" \

  -F "prompt=Add a starry night sky to this image" \

  -F "size=1024x1024"

# Response:

# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

import OpenAI from 'openai';

import fs from 'fs';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

  baseURL: 'https://api.lumenfall.ai/openai/v1'

});

const response = await client.images.edit({

  model: 'gemini-3.1-flash-image-preview',

  image: fs.createReadStream('source.png'),

  prompt: 'Add a starry night sky to this image',

  size: '1024x1024'

});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

console.log(response.data[0].url);

from openai import OpenAI

client = OpenAI(

    api_key="YOUR_API_KEY",

    base_url="https://api.lumenfall.ai/openai/v1"

response = client.images.edit(

    model="gemini-3.1-flash-image-preview",

    image=open("source.png", "rb"),

    prompt="Add a starry night sky to this image",

    size="1024x1024"

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

print(response.data[0].url)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Text prompt for image generation	T2I Edit
`seed`	integer	Random seed for reproducibility	T2I Edit

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9") WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	T2I Edit
`aspect_ratio`	string	Aspect ratio of the output image (e.g. "16:9", "1:1") Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	T2I Edit
`resolution`	string	Output resolution tier (e.g. "1K", "4K") `auto` `0.5K` `1K` `2K` `4K` Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	T2I Edit

Output	`size`		`aspect_ratio` + `resolution`
Flexible
Auto	`"auto"`	—	Model chooses optimal dimensions

0.5K 14 sizes

Output	`size`		`aspect_ratio` + `resolution`
573 × 458	`"573x458"`	or	`"5:4"` + `"0.5K"`
384 × 683	`"384x683"`	or	`"9:16"` + `"0.5K"`
683 × 384	`"683x384"`	or	`"16:9"` + `"0.5K"`
256 × 1024	`"256x1024"`	or	`"1:4"` + `"0.5K"`
512 × 512	`"512x512"`	or	`"1:1"` + `"0.5K"`
1024 × 256	`"1024x256"`	or	`"4:1"` + `"0.5K"`
181 × 1448	`"181x1448"`	or	`"1:8"` + `"0.5K"`
1448 × 181	`"1448x181"`	or	`"8:1"` + `"0.5K"`
418 × 627	`"418x627"`	or	`"2:3"` + `"0.5K"`
627 × 418	`"627x418"`	or	`"3:2"` + `"0.5K"`
458 × 572	`"458x572"`	or	`"4:5"` + `"0.5K"`
782 × 335	`"782x335"`	or	`"21:9"` + `"0.5K"`
443 × 591	`"443x591"`	or	`"3:4"` + `"0.5K"`
591 × 443	`"591x443"`	or	`"4:3"` + `"0.5K"`

1K 14 sizes

Output	`size`		`aspect_ratio` + `resolution`
1183 × 887	`"1183x887"`	or	`"4:3"` + `"1K"`
916 × 1145	`"916x1145"`	or	`"4:5"` + `"1K"`
1145 × 916	`"1145x916"`	or	`"5:4"` + `"1K"`
512 × 2048	`"512x2048"`	or	`"1:4"` + `"1K"`
1024 × 1024	`"1024x1024"`	or	`"1:1"` + `"1K"`
2048 × 512	`"2048x512"`	or	`"4:1"` + `"1K"`
887 × 1182	`"887x1182"`	or	`"3:4"` + `"1K"`
362 × 2896	`"362x2896"`	or	`"1:8"` + `"1K"`
2896 × 362	`"2896x362"`	or	`"8:1"` + `"1K"`
836 × 1254	`"836x1254"`	or	`"2:3"` + `"1K"`
1254 × 836	`"1254x836"`	or	`"3:2"` + `"1K"`
768 × 1365	`"768x1365"`	or	`"9:16"` + `"1K"`
1365 × 768	`"1365x768"`	or	`"16:9"` + `"1K"`
1563 × 670	`"1563x670"`	or	`"21:9"` + `"1K"`

2K 14 sizes

Output	`size`		`aspect_ratio` + `resolution`
3129 × 1341	`"3129x1341"`	or	`"21:9"` + `"2K"`
1774 × 2365	`"1774x2365"`	or	`"3:4"` + `"2K"`
2365 × 1774	`"2365x1774"`	or	`"4:3"` + `"2K"`
1832 × 2290	`"1832x2290"`	or	`"4:5"` + `"2K"`
2290 × 1832	`"2290x1832"`	or	`"5:4"` + `"2K"`
1536 × 2731	`"1536x2731"`	or	`"9:16"` + `"2K"`
2731 × 1536	`"2731x1536"`	or	`"16:9"` + `"2K"`
1024 × 4096	`"1024x4096"`	or	`"1:4"` + `"2K"`
2048 × 2048	`"2048x2048"`	or	`"1:1"` + `"2K"`
4096 × 1024	`"4096x1024"`	or	`"4:1"` + `"2K"`
724 × 5793	`"724x5793"`	or	`"1:8"` + `"2K"`
5792 × 724	`"5792x724"`	or	`"8:1"` + `"2K"`
1672 × 2508	`"1672x2508"`	or	`"2:3"` + `"2K"`
2508 × 1672	`"2508x1672"`	or	`"3:2"` + `"2K"`

4K 14 sizes

Output	`size`		`aspect_ratio` + `resolution`
3548 × 4730	`"3548x4730"`	or	`"3:4"` + `"4K"`
3345 × 5017	`"3345x5017"`	or	`"2:3"` + `"4K"`
4580 × 3664	`"4580x3664"`	or	`"5:4"` + `"4K"`
2048 × 8192	`"2048x8192"`	or	`"1:4"` + `"4K"`
4096 × 4096	`"4096x4096"`	or	`"1:1"` + `"4K"`
8192 × 2048	`"8192x2048"`	or	`"4:1"` + `"4K"`
3072 × 5461	`"3072x5461"`	or	`"9:16"` + `"4K"`
5461 × 3072	`"5461x3072"`	or	`"16:9"` + `"4K"`
1448 × 11585	`"1448x11585"`	or	`"1:8"` + `"4K"`
4729 × 3547	`"4729x3547"`	or	`"4:3"` + `"4K"`
11584 × 1448	`"11584x1448"`	or	`"8:1"` + `"4K"`
5016 × 3344	`"5016x3344"`	or	`"3:2"` + `"4K"`
3663 × 4579	`"3663x4579"`	or	`"4:5"` + `"4K"`
6256 × 2681	`"6256x2681"`	or	`"21:9"` + `"4K"`

How these parameters work

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Media Inputs

Parameter	Type	Description	Modes
`image`	file	Required. Input image(s) to edit Supports PNG, JPEG, WebP.	T2I Edit

Output & Format

Parameter	Type	Description	Modes
`response_format`	string	How to return the image `url` `b64_json` Default: `"url"`	T2I Edit
`output_format`	string	Output image format `png` `jpeg` `gif` `webp` `avif` Gateway converts to requested format if provider doesn't support it natively.	T2I Edit
`output_compression`	integer	Compression level for lossy formats (JPEG, WebP, AVIF)	T2I Edit
`n`	integer	Number of images to generate Default: `1` Gateway generates multiple images in parallel even if provider only supports 1.	T2I Edit

Additional Parameters

Parameter	Type	Description	Modes
`enable_web_search` fal	boolean	Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.	T2I Edit
`google_search` replicate	boolean	Use Google Web Search grounding to generate images based on real-time information (e.g. weather, sports scores, recent events).	T2I Edit
`image_search` replicate	boolean	Use Google Image Search grounding to find web images as visual context for generation. When enabled, web search is also used automatically.	T2I Edit
`limit_generations` fal	boolean	Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.	T2I Edit
`safety_tolerance` fal	string	The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. `1` `2` `3` `4` `5` `6`	T2I Edit
`sync_mode` fal	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	T2I Edit
`thinking_level` fal	string	When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable. `high` `minimal`	T2I Edit

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Nano Banana 2 Benchmarks

Nano Banana 2 (Gemini 3.1 Flash Image) ranks #1 in text-to-image generation with an Elo of 1302 and #6 in image editing with an Elo of 1223. This high-efficiency model demonstrates top-tier performance against competitors, maintaining competitive rankings across both creative and technical generation tasks.

Lumenfall Arena

Image Editing

1241 Elo

Lumenfall Arena

Text-to-Image

1293 Elo

Image Editing Landscape

Elo vs Cost

Elo vs Speed

1 model waiting for enough speed data

Text-to-Image Landscape

Elo vs Cost

1 model without pricing omitted

Elo vs Speed

8 models waiting for enough speed data

Competition Results

Image Editing

Photorealism

View leaderboard

Man and Car in California

13 models

Image Editing

Source

Edit instruction

“Make a photo of the man driving the car down the California coastline”

Nano Banana 2 edited result for Bald man challenge

Original image before Nano Banana 2 editing

Before After

Bald man challenge

15 models

Image Editing

Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Nano Banana 2 edited result for Neutral Expression to Genuine Smile

Before After

Neutral Expression to Genuine Smile

14 models

Image Editing

Edit instruction

{
  "action": "image_edit",
  "reference": "uploaded neutral portrait",
  "change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
  "details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
  "preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
  "no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
  "style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}

Nano Banana 2 edited result for Night Sky Transformation

Before After

#10

Night Sky Transformation

16 models

Image Editing

Edit instruction

“Change the scene to night: a deep, dark sky with subtle, glistening stars visible behind the mountain.”

Text-to-Image

Text Rendering

View leaderboard

Modern Clean Menu

19 models

Text-to-Image

Prompt

“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”

Vintage Cafe Logo

21 models

Text-to-Image

Prompt

“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”

Apollo 11: Journey to Tranquility

19 models

Text-to-Image

Prompt

“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”

Image Editing

Anime

View leaderboard

Studio Ghibli Anime Style

14 models

Image Editing

Source

Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Image Editing

Portrait

View leaderboard

Before After

Bald man challenge

15 models

Image Editing

Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After

Neutral Expression to Genuine Smile

14 models

Image Editing

Edit instruction

{
  "action": "image_edit",
  "reference": "uploaded neutral portrait",
  "change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
  "details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
  "preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
  "no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
  "style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}

Text-to-Image

Photorealism

View leaderboard

#10

Candid Street Photography

24 models

Text-to-Image

Prompt

“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”

Text-to-Image

Product, Branding & Commercial

View leaderboard

Vintage Cafe Logo

21 models

Text-to-Image

Prompt

Text-to-Image

Portrait

View leaderboard

Fantasy Warrior

21 models

Text-to-Image

Prompt

“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”

Uncategorized

Over-the-top cartoon caricature

13 models

Image Editing

Source

Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Geometric Composition

22 models

Text-to-Image

Prompt

“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”

Adorable Baby Animals in Sunny Meadow

25 models

Text-to-Image

Prompt

“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”

#10

Isometric Miniature Diorama Scenes

21 models

Text-to-Image

Prompt

“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”

Top Matchups

See how Nano Banana 2 performs head-to-head against other AI models, ranked by community votes in blind comparisons.

vs Nano Banana Pro

Challenge: Over-the-top cartoon caricature

50% W · 50% L

vs FLUX.2 [dev] Turbo

Challenge: Geometric Composition

50% W · 50% L

vs GPT Image 1.5

Challenge: Vintage Cafe Logo

100% W · 0% L

vs Grok Imagine Image

Challenge: Modern Clean Menu

0% W · 100% L

vs Reve Image 1.0

Challenge: Night Sky Transformation

0% W · 100% L

Nano Banana 2 is best for

See all Use Cases

The model excels in Product, Branding, and Commercial categories with a 100% win rate and secures a #2 rank for text rendering at 93.5% accuracy. While dominant in commercial design and text integration, it shows comparatively lower performance in photorealism where it ranks #13 of 22 models.

#1 of 14

Anime

Edit · 66.7% win rate

#1 of 21

Portrait

Gen · 75.0% win rate

#1 of 22

Product, Branding & Commercial

Gen · 94.1% win rate

#2 of 15

Portrait

Edit · 88.2% win rate

#3 of 24

Text Rendering

Gen · 82.4% win rate

#3 of 16

Photorealism

Edit · 61.5% win rate

Gallery

View all 19 images

Nano Banana 2 FAQ

How much does Nano Banana 2 cost?

Nano Banana 2 starts at $0.0225 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

What can Nano Banana 2 do?

Nano Banana 2 supports Function calling, Structured output, Batch, Streaming, System prompt, Tool use, Grounding, Thinking, Code execution, and Json mode. It accepts text, image, audio, video, and file input and produces text and image output.

How do I use Nano Banana 2 via API?

You can use Nano Banana 2 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "gemini-3.1-flash-image-preview". Code examples are available in Python, JavaScript, and cURL.

Which providers offer Nano Banana 2?

Nano Banana 2 is available through Vertex AI, fal.ai, Replicate, and Gemini API on Lumenfall. Lumenfall automatically routes requests to the best available provider.

Overview

Nano Banana 2 (slug: gemini-3.1-flash-image-preview) is a high-efficiency multimodal model developed by Google that bridges the gap between reasoning and visual synthesis. As the streamlined counterpart to the Gemini 3 Pro Image, it provides a unified interface for complex text generation and fast image creation. It is distinctive for its “Thinking Mode,” allowing the model to perform internal reasoning cycles before generating an image or structured text response.

Strengths

High-Efficiency Generation: Optimized for speed and low latency, making it suitable for real-time applications where rapid image iteration is required.
Complex Text Rendering: Excels at incorporating legible, accurate typography within generated images, a common failure point for many diffusion-based models.
Deep Reasoning Integration: Features a native thinking mode that allows the model to process complex prompts, spatial relationships, and logical constraints before producing visual or textual output.
Grounding and Tool Use: Supports search grounding and code execution, enabling the model to verify facts or perform calculations prior to generating content.
Reference Image Support: Capable of using existing images as structural or stylistic guides to maintain consistency across generated assets.

Limitations

Efficiency vs. Fidelity: While fast, it may lack the extreme aesthetic refinement and intricate textural detail found in the larger Gemini 3 Pro Image model.
Preview Status: As a preview release, the model may exhibit occasional inconsistencies in following highly nuanced stylistic prompts compared to more mature, production-stable versions.
Context Overhead: The use of internal reasoning (Thinking Mode) can increase processing time for simple tasks where a direct generation would have sufficed.

Technical Background

Part of the Gemini 3.1 Flash family, this model utilizes a multimodal transformer architecture trained for both discriminative and generative tasks. It integrates a latent diffusion-based image generation head directly into the language model pipeline, allowing for seamless transitions between modalities. By employing a “distilled” training approach, Google has optimized the model for high throughput while retaining the core reasoning capabilities of the Gemini 3.1 architecture.

Best For

Nano Banana 2 is ideal for building interactive design tools, rapid prototyping of social media assets, and automated content pipelines where both text and imagery are required. Its support for structured output and JSON mode makes it an excellent choice for developers needing to programmatically control visual attributes. You can experiment with these multimodal features and integrate them into your workflow through Lumenfall’s unified API and playground.

Try Nano Banana 2 in Playground

Generate images with custom prompts — no API key needed.

Open Playground