NANO-BANANA
Creates a highly realistic hand-drawn pen sketch effect with natural line pressure, detailed cross-hatching, and authentic paper texture, while preserving the subject’s proportions and overall identity
Avg Run Time: 65.000s
Model Slug: nano-banana-pro-sketch
Release Date: December 8, 2025
Playground
Input
Enter a URL or choose a file from your computer.
Invalid URL.
(Max 50MB)
Output
Example Result
Preview and download your result.
API & SDK
Create a Prediction
Send a POST request to create a new prediction. This will return a prediction ID that you'll use to check the result. The request should include your model inputs and API key.
Get Prediction Result
Poll the prediction endpoint with the prediction ID until the result is ready. The API uses long-polling, so you'll need to repeatedly check until you receive a success status.
Readme
Overview
nano-banana-pro-sketch — Image-to-Image AI Model
Developed by Google as part of the nano-banana family powered by Gemini 3 Pro Image architecture, nano-banana-pro-sketch transforms uploaded images into highly realistic hand-drawn pen sketches with natural line pressure, detailed cross-hatching, and authentic paper texture while preserving the subject's proportions and identity. This image-to-image AI model excels at converting photos into professional sketch art, ideal for designers seeking Google image-to-image tools that mimic traditional pen-and-ink techniques without losing original fidelity. Unlike generic filters, it delivers studio-quality outputs grounded in advanced reasoning for precise stylistic control.
Technical Specifications
What Sets nano-banana-pro-sketch Apart
nano-banana-pro-sketch stands out in the competitive landscape of image-to-image AI models through its Gemini 3 Pro integration, enabling fact-based enhancements and superior stylistic rendering for sketch effects. It supports up to 4K resolution (3840 x 2160 px) for professional-grade outputs suitable for printing or billboards, with flexible aspect ratios like 16:9 or 9:16, and processes most edits in about 10 seconds.
- Realistic sketch simulation with natural line pressure and cross-hatching: Analyzes input images to apply authentic pen stroke variations and paper textures, enabling artists to turn product photos into illustrative marketing visuals that feel hand-crafted.
- Multi-image reference for consistent style (up to 14 references): Maintains brand elements like logos or character appearances across sketch series, perfect for scalable storytelling in design workflows.
- Knowledge-grounded sketch refinement via Google Search: Incorporates real-world context for accurate details, such as sketching specific plant species with factual annotations, outperforming basic stylization tools.
These capabilities make it a top choice for nano-banana-pro-sketch API integrations in high-precision creative apps.
Key Considerations
Tips & Tricks
How to Use nano-banana-pro-sketch on Eachlabs
Access nano-banana-pro-sketch seamlessly through Eachlabs Playground for instant testing—upload an input image, add a prompt like "convert to realistic pen sketch with cross-hatching," select 4K resolution and aspect ratio, and generate in seconds. Integrate via Eachlabs API or SDK with parameters for image references (up to 14), style strength, and output format, delivering high-fidelity PNGs with SynthID watermarking for commercial use.
---Capabilities
What Can I Use It For?
Use Cases for nano-banana-pro-sketch
For graphic designers, nano-banana-pro-sketch turns rough iPad sketches or paper drawings into polished pen-and-ink illustrations with realistic shading and texture, preserving every detail for client presentations—upload a photo of your concept art and prompt for "refine into detailed cross-hatched pen sketch on textured paper."
Marketers building AI image editor API tools for e-commerce can input product photos alongside brand references, generating sketch-style mockups that maintain proportions and add hand-drawn appeal for social media campaigns, streamlining localized visuals without photography sessions.
Developers integrating Google image-to-image for apps photograph real-world objects like plants, then use the model to create educational infographic sketches with accurate labels pulled from Google Search knowledge, ensuring factual precision in outputs for edtech platforms.
UX designers experiment with scene variations by uploading wireframes and applying sketch effects with adjustable lighting or focus, producing consistent style series for storyboards that guide stakeholder feedback in agile workflows.
Things to Be Aware Of
Limitations
Pricing
Pricing Detail
This model runs at a cost of $0.15 per execution.
Pricing Type: Fixed
The cost remains the same regardless of which model you use or how long it runs. There are no variables affecting the price. It is a set, fixed amount per run, as the name suggests. This makes budgeting simple and predictable because you pay the same fee every time you execute the model.
Related AI Models
You can seamlessly integrate advanced AI capabilities into your applications without the hassle of managing complex infrastructure.
A face swap model automatically replaces the face in an image with another face while preserving expressions, lighting, and overall realism
FLUX.2 [dev] from Black Forest Labs provides turbo-speed image-to-image editing with precise control through natural-language instructions and hex color adjustments.
Creates images from text and reference images with custom LoRA support, powered by Tongyi-MAI’s ultra-fast 6B Z-Image Turbo model for rapid, high-quality generation.
Generates images from text combined with edge, depth, or pose inputs using Tongyi-MAI’s ultra-fast 6B Z-Image Turbo model for precise and high-quality results.
