Back: Catalog

screenshot-to-code

It is a tool that converts screenshots, Figma designs, and screen recordings into HTML, React, Vue, or Ionic-based codes using AI. It runs with a FastAPI-based backend and React/Vite front; it supports a variety of language models such as Gemini, GPT and Claude. Users can run the project locally or use its hosted version.

SC

screenshot-to-code

95

abi · AI / LLM / RAG

STARS80.9K
FORKS9.9K
COMMITS1.3K
CONTRIBUTORS26
VERSION—
UPDATED4 days ago
PythonUI ÜretimiGPT-4oClaude VisionMIT

Common commercial products in this category: ChatGPT, Claude, Gemini

What can it do?
  • You can convert screenshots or Figma designs into HTML and React components with Tailwind CSS support.
  • You can turn these records into functional prototypes by taking screenshots of their website.
  • Using Gemini and Replicate API keys, you can extract assets from the images or perform background cleaning operations.
User reviews
  • • NeutralGitHub Issue

    Error generating code. Check the Developer Console AND the backend logs for details. Feel free to open a Github issue.

    “After clicking "update", two Error generating code were prompted. Check the Developer Console AND the backend logs for details. Feel free to open a Github issue. 1. I confirmed that my apikey can use gpt-4-vision-preview 2. I ran it through docker-compose and first ran echo…”

  • • NeutralGitHub Issue

    RUN ERROR OF MAC OS ?????

    “VITE v4.5.0 ready in 1254 ms ➜ Local: 14:06:21 ➜ Network: use --host to expose 14:06:21 ➜ press h to show help 14:06:21 ERROR 14:06:25 [TypeScript] Found 0 errors. Watching for file changes.”

Website GitHub

Verified against README · Oct 26, 2026 · source

My note

Alternative pages

ChatGPT alternativesClaude alternativesGemini alternatives

More in: AI / LLM / RAG