AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Photographers › ui-screenshot-to-prompt
✦ Free & open sourcePhotographers

ui-screenshot-to-prompt

Converts UI screenshots into detailed implementation prompts for AI coding assistants.

Turn UI Screenshots into AI Build Prompts

Extract components, layouts, and text from design mockups to feed coding copilots.

Free forever · open source · MIT
✓ Light setup✓ Browser-based✓ Real-time collaboration
5.6
ZEKAI
Handy UI-to-prompt pipeline
Free & open source · Photographers
Ease of setup5
Usefulness7
Maintenance5.5
Community5
★ 238
GITHUB
Oct 2025
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

This tool translates static UI screenshots into structured implementation briefs using computer vision and language models. It suits developers and designers working with AI coding tools like Bolt.new or v0 who want to bridge the gap between design and code.

Runs on
Cross-platform
Hosting
Desktop
Languages
Python
License
MIT

What it is

It parses UI images through a pipeline featuring basic grid slicing and experimental EasyOCR with OpenCV detection. OpenAI vision models analyze the regions before a secondary Claude or OpenRouter pass finalizes the instructions for an AI coding copilot.

Who it's for

It suits developers and technical designers using AI coding workflows who need automated text and layout extraction from mockups. It does not suit non-technical users looking for a direct image-to-code compiler without managing API keys and command-line interfaces.

Key features

Basic grid slicing

Provides deterministic spatial summaries for rapid layout analysis.

Advanced component detection

Uses EasyOCR and OpenCV to extract likely UI elements from the image.

Multi-model vision pipeline

Combines OpenAI vision models for region analysis with Claude or OpenRouter for final instructions.

Gradio drag-and-drop UI

Offers a local web interface so you can drop screenshots without touching the CLI.

How to start

Up and running in 3 steps

1
Clone the repository and navigate into the project directory via your terminal
2
Set up your environment using uv and copy the example environment file to add your API keys
3
Run the local Gradio application using the provided python command
Real talk

Our honest verdict

What's great

  • Includes a Gradio front-end for drag-and-drop usage instead of manual CLI execution
  • Supports multiple LLM vendors like OpenAI, Anthropic, and OpenRouter for the prompt assembly pass
  • Features a CPU-friendly pipeline that downloads EasyOCR weights automatically on the first run
  • Provides a deterministic basic mode for fast spatial summaries alongside experimental advanced detection

Where it falls short

  • Requires you to supply and pay for your own OpenAI and optional Anthropic or OpenRouter API keys
  • Advanced detection mode is experimental and still prone to generating false positives
  • Requires command-line familiarity with Git, Python, and uv package manager to install and run
Cost

Pricing & license

The software is free under its MIT license, but running it requires paying for the necessary OpenAI, Anthropic, or OpenRouter API usage.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives
Get more

Use it, or have us set it up

📄 Free PDF: ui-screenshot-to-prompt for Photographers
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure ui-screenshot-to-prompt for you — and train your team.
Get it done for you ↗
Questions

FAQ

What AI models are required to run this tool?

OpenAI Vision is required for region analysis, while Anthropic or OpenRouter keys are optional to improve the final prompt.

Can I run this without a GPU?

Yes, the project is CPU-friendly and EasyOCR will download its required weights on the first run.

How do I use the web interface?

After installing dependencies and configuring your keys, run the main python module to launch the Gradio front-end locally.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Photographers — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google