In-Depth

Hands On: New VS Code Insiders Build Creates Web Page from Image in Seconds

New Vision support with GitHub Copilot in the latest Visual Studio Code Insiders build takes a user-supplied mockup image and creates a web page from it in seconds, handling all the HTML and CSS.

Microsoft announced the new Vision support, along with Agent mode and a preview of next-edit suggestions (NES), last week, providing a peek into the future of coding. Here's a summary of the three new features:

  • Next Edit Suggestions (NES): This feature enhances AI-powered code completions by predicting and suggesting the next edits a developer might want to make in existing code. As code is modified, NES anticipates subsequent changes, allowing devs to navigate and accept suggestions using the Tab key. An arrow in the gutter indicates available edit suggestions, streamlining the editing process.
  • Agent Mode for Copilot Edits: Agent Mode offers an autonomous editing experience where Copilot plans and executes tasks to fulfill requests. It determines relevant files, applies code changes, suggests terminal commands, and iterates to resolve issues, all while keeping users in control to review and confirm actions.
  • Vision: This enables Copilot to generate code based on visual inputs like screenshots or markup. By analyzing visual data, Copilot can create corresponding user interfaces or provide descriptive alt text for images, bridging the gap between visual design and code implementation.

The latter, this reporter found, works great.

In a proof-of-concept that only took a few minutes overall, I had ChatGPT generate a mockup image of a web page, which I then fed to VS Code Insiders. The Insiders Copilot created a web page from the image, handling all the HTML and CSS in seconds.

ChatGPT 4o still has some image-generation issues, especially when it tries to incorporate text, but it did generate this mockup:

AI-Generated Mockup Image
[Click on image for larger view.] AI-Generated Mockup Image (source: Ramel).

Even that degraded image worked fine.

I clicked on the Copilot icon in the Activity Bar to open Chat, then dragged the image into the Chat window, with instructions to generate a web page, which I saved as an HTML file.

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Webpage Design</title>
    <link rel="stylesheet" href="styles.css">
</head>
<body>
    <header>
        <nav>
            <ul>
                <li><a href="#">Home</a></li>
                <li><a href="#">About</a></li>
                <li><a href="#">Services</a></li>
                <li><a href="#">Contact</a></li>
            </ul>
        </nav>
    </header>
    <main>
        <section class="hero">
            <h1>Home</h1>
            <p>Some introductory text about the website.</p>
        </section>
        <section class="content">
            <div class="main-content">
                <img src="image1.jpg" alt="Main Image">
                <p>Main content description goes here.</p>
            </div>
            <div class="sidebar">
                <div class="sidebar-item">
                    <h2>Home</h2>
                    <p>Some text about Home.</p>
                </div>
                <div class="sidebar-item">
                    <h2>About</h2>
                    <p>Some text about About.</p>
                </div>
                <div class="sidebar-item">
                    <h2>Services</h2>
                    <p>Some text about Services.</p>
                </div>
                <div class="sidebar-item">
                    <h2>Contact</h2>
                    <p>Some text about Contact.</p>
                </div>
            </div>
        </section>
    </main>
    <footer>
        <p>&copy; 2025 Webpage Design. All rights reserved.</p>
    </footer>
</body>
</html>

It also generated the CSS:

body {
    font-family: Arial, sans-serif;
    margin: 0;
    padding: 0;
    background-color: #f0f0f0;
}

header {
    background-color: #fff;
    padding: 10px 0;
    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
}

nav ul {
    list-style: none;
    display: flex;
    justify-content: center;
    padding: 0;
    margin: 0;
}

nav ul li {
    margin: 0 15px;
}

nav ul li a {
    text-decoration: none;
    color: #333;
    font-weight: bold;
}

.hero {
    text-align: center;
    padding: 50px 20px;
    background-color: #fff;
}

.hero h1 {
    font-size: 3em;
    margin: 0;
}

.hero p {
    font-size: 1.2em;
    color: #666;
}

.content {
    display: flex;
    justify-content: center;
    padding: 20px;
}

.main-content {
    flex: 2;
    margin-right: 20px;
}

.main-content img {
    width: 100%;
    height: auto;
    border-radius: 10px;
}

.sidebar {
    flex: 1;
    display: flex;
    flex-direction: column;
    gap: 20px;
}

.sidebar-item {
    background-color: #fff;
    padding: 20px;
    border-radius: 10px;
    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
}

.sidebar-item h2 {
    margin-top: 0;
}

footer {
    text-align: center;
    padding: 20px;
    background-color: #fff;
    box-shadow: 0 -2px 4px rgba(0, 0, 0, 0.1);
}

I only needed to place an "image1" for the web page in the same directory as the HTML file along with a styles.css file. That gave me this:

Generated Site
[Click on image for larger view.] Generated Site (source: Ramel).

That's obviously not a recreation of the supplied mockup image, but it provides a great head start.

I asked my in-house Copilot how long it would take a user to code all that up by hand and it estimated 30-45 minutes, noting, "This estimate assumes the developer is familiar with HTML and CSS and does not include time for additional features or extensive testing."

As far as the other two previews, check out "GitHub Previews Agentic AI in VS Code Copilot" and "VS Code Copilot Gets Closer to Tab, Tab, Tab Coding."

About the Author

David Ramel is an editor and writer at Converge 360.

comments powered by Disqus

Featured

  • Hands On: New VS Code Insiders Build Creates Web Page from Image in Seconds

    New Vision support with GitHub Copilot in the latest Visual Studio Code Insiders build takes a user-supplied mockup image and creates a web page from it in seconds, handling all the HTML and CSS.

  • Naive Bayes Regression Using C#

    Dr. James McCaffrey from Microsoft Research presents a complete end-to-end demonstration of the naive Bayes regression technique, where the goal is to predict a single numeric value. Compared to other machine learning regression techniques, naive Bayes regression is usually less accurate, but is simple, easy to implement and customize, works on both large and small datasets, is highly interpretable, and doesn't require tuning any hyperparameters.

  • VS Code Copilot Previews New GPT-4o AI Code Completion Model

    The 4o upgrade includes additional training on more than 275,000 high-quality public repositories in over 30 popular programming languages, said Microsoft-owned GitHub, which created the original "AI pair programmer" years ago.

  • Microsoft's Rust Embrace Continues with Azure SDK Beta

    "Rust's strong type system and ownership model help prevent common programming errors such as null pointer dereferencing and buffer overflows, leading to more secure and stable code."

  • Xcode IDE from Microsoft Archrival Apple Gets Copilot AI

    Just after expanding the reach of its Copilot AI coding assistant to the open-source Eclipse IDE, Microsoft showcased how it's going even further, providing details about a preview version for the Xcode IDE from archrival Apple.

Subscribe on YouTube

Upcoming Training Events