Turning a rough sketch into a prototype
Upload a simple page drawing and get a first React implementation that can be refined by a developer.
Independent tool overview
Napkins.dev is a free, open-source wireframe-to-app generator that turns a screenshot or sketch into a runnable React and Tailwind prototype.
Visit the official Napkins.dev site ↗
Overview
Napkins.dev has one focused workflow: upload an image of a web interface and generate a matching front-end app. The current hosted version uses Kimi K2.5 through Together AI and renders the result in a browser sandbox.
It is useful for converting a hand-drawn wireframe, mockup, or screenshot into an initial React and Tailwind implementation. Developers can then inspect, copy, and revise the generated code rather than starting every layout from an empty file.
Napkins.dev is a prototype generator, not a complete application platform. It does not infer a secure backend, data model, permissions, accessibility behavior, business rules, testing strategy, or production deployment from a screenshot.
Use cases
The strongest fit depends on the job you need the product to complete, not the size of its feature list.
Upload a simple page drawing and get a first React implementation that can be refined by a developer.
Use a screenshot as layout inspiration when the goal is to rebuild the structure and styling in a modern front-end stack.
Make a runnable version of a static concept before spending time on full design-system and application work.
Study or customize an MIT-licensed Next.js application that combines visual model inference, S3 image storage, and Sandpack preview.
Capabilities
Analyzes the uploaded interface image and writes React components styled with Tailwind CSS.
Works with rough interface sketches as well as polished screenshots, making it useful before a high-fidelity design exists.
Loads the generated project in Sandpack so users can inspect the result without setting up a local development environment first.
The MIT-licensed repository exposes the Next.js app, prompts, model integration, storage setup, and preview architecture.
Developers can run their own deployment with a Together AI API key and compatible S3 object storage.
Process
Step 1
Crop to one page or state, use readable spacing and contrast, and remove unrelated browser chrome or confidential information.
Step 2
Submit the screenshot or wireframe and let the current vision-language model produce a React and Tailwind interpretation.
Step 3
Check hierarchy, responsive intent, component boundaries, and interaction states before spending time on exact colors and spacing.
Step 4
Adapt generated components to the application's framework, design tokens, routes, data layer, authentication, and existing component library.
Step 5
Review accessibility, responsiveness, browser support, performance, security, tests, licensing, and visual accuracy before shipping.
Cost
Napkins.dev's hosted generator is currently available without a published paid plan. The source code is free under the MIT license. A self-hosted deployment still incurs Together AI inference, S3-compatible storage, hosting, monitoring, and engineering costs.
Free
Use the public screenshot-to-app demo without a published subscription tier.
No software license fee
Run and modify the MIT-licensed application on your own infrastructure.
Pricing checked . Check current pricing at the source ↗
Assessment
Compare
The right alternative depends on the specific output, workflow, controls and budget your project requires.
Design
Choose Vercel v0 for a more full-featured prompt-and-image UI builder with an ongoing conversational editing workflow.
Explore Vercel v0 →Coding
Choose Lovable when the goal is a broader full-stack application with backend integrations and deployment, not just screenshot-derived front-end code.
Explore Lovable →Coding
Choose Bolt for browser-based full-app generation, package installation, and iterative coding from natural-language requirements.
Explore Bolt.new →Questions
It turns an uploaded wireframe, sketch, mockup, or screenshot into a runnable React front end styled with Tailwind CSS.
Yes. The public generator has no published paid plan, and the source code is available under the MIT license. Self-hosting still costs money for model inference, storage, and hosting.
Yes. The official Nutlope/napkins repository is public under the MIT license.
The current hosted page and repository identify Kimi K2.5 served through Together AI. Older articles may refer to earlier Llama vision models used by previous versions.
It can create a useful front-end starting point, but a screenshot cannot define backend logic, security, data, permissions, accessibility, tests, or production operations. Those still require implementation and review.
Yes. The repository documents local deployment with a Together AI API key, S3-compatible image storage credentials, and the normal Next.js dependencies.
Bottom line
Napkins.dev is a good lightweight accelerator when a visual reference already exists and a developer wants a React/Tailwind starting point. Its open source and narrow scope are advantages, but the generated result should be treated as disposable prototype code until it has been integrated with the real design system, application logic, accessibility requirements, and tests.
Visit Napkins.dev website ↗
Build generative AI models with expert support.

Observability platform for managing LLM performance.

Multimodal language model for diverse applications.

Meta Llama Models: Llama models from meta offer open-source, state-of-the-art foundational models for research and deployment.

Get access to all our AI courses, hundreds of real-world AI use cases, live expert-led workshops, an exclusive network of AI early adopters, and more.
Get unlimited access to all of our current & upcoming industry-specific AI courses for the duration of your subscription.
To keep up with the rapid pace of AI, our team publishes AI implementation guides daily. Our library contains 300+ practical use cases to automate real-world work.
Join weekly, live, interactive sessions with industry leaders who are at the forefront of AI for hands-on implementation guidance and exclusive insights.
Network with an exclusive community of AI-first professionals who are working smarter with AI. Learn how early adopters are using AI in their work and businesses.