In partnership with

THE SIGNAL

You probably saw five "revolutionary" AI tools on your feed today. You'll realistically try zero.

So today's signal is just one workflow I actually used to build a portfolio landing page that looks like I spent weeks in Figma.

Total time: 30 minutes. Total cost: $0.50.

Generate two images. Drop one prompt. Deploy.

WORKFLOW DROP
AI Studio + Claude Opus 4.6

This combo generates a full-screen hero landing page with cursor effects, parallax, and reveal animations.

No Figma. No CSS wrangling. No hiring a designer.

Who it's for:
- Founders needing a quick portfolio
- Creators building a personal brand
- Anyone tired of blank-page syndrome

What it actually does:

1. Generate two matching portraits (one plain, one wearing a helmet/glasses/whatever)

2. Drop a single prompt into Claude with your images

3. Get a deployable landing page with:
- Circular cursor reveal effect
- Motion echoes on fast movement
- Subtle animated grid background
- Text inversion on hover
- Light parallax effect

What it sucks at:
- Sometimes the images don't align perfectly (I'll show you the fix)
- You need to regenerate a few times to get the pose right
- Not for complex multi-page sites (yet)

→ Try it yourself: Copy the prompts below

The Tech newsletter for Engineers who want to stay ahead

Tech moves fast, but you're still playing catch-up?

That's exactly why 100K+ engineers working at Google, Meta, and Apple read The Code twice a week.

Here's what you get:

  • Curated tech news that shapes your career - Filtered from thousands of sources so you know what's coming 6 months early.

  • Practical resources you can use immediately - Real tutorials and tools that solve actual engineering problems.

  • Research papers and insights decoded - We break down complex tech so you understand what matters.

All delivered twice a week in just 2 short emails.

Step 1: Go to AI Studio

- Temperature: 1
- Aspect Ratio: 9:16 (TikTok format)
- Resolution: Start in 1K for testing, then regenerate in 4K

Pro tip: Test everything in 1K first. Once you're happy, regenerate with the prompt "generate this image in 4k" to save credits.

Step 2: The Image Prompt That Works

Copy this exactly. It generates insane detail.

```
Extreme macro close up of [FACIAL AREA / BODY PART — or "this person" with image reference].
Photorealistic detail with visible [PRIMARY TEXTURES: pores, fine hairs, wrinkles, fibers]. Natural imperfections including [SUBTLE FLAWS: redness, uneven tone, tiny blemishes]. Realistic surface variation with natural oil sheen and dryness in different areas. No makeup, no retouching.
Surrounding skin shows authentic texture with visible pores, micro details, and natural asymmetry. Real skin translucency, no idealized smoothness.
Lighting is soft but directional, grazing the surface at a shallow angle to reveal texture and depth. Neutral white balance, true to life color science, cinematic contrast. No crushed blacks, no blown highlights. Ultra shallow depth of field with critical focus on the surface, gentle falloff toward the edges.
Shot on a high end macro lens, 100mm macro equivalent. Feels like a real DSLR or smartphone macro capture. Documentary realism, unretouched, raw and authentic. Not CGI.
Same exact position, same exact posture, same exact angle.
```

If generating from scratch: Replace the bracketed part with a detailed description like "albino model with piercing blue eyes, sharp jawline, looking directly at camera"

Budget option: Cream V4.5 on WaveSpeed AI — 5x cheaper (~4 cents per image), same workflow.

Step 3: Generate Two Matching Images

This is where everyone messes up.

You need:
1. Base image: just you, no props
2. Variant image: same exact position, same posture, same angle, but with something on your head (helmet, astronaut helmet, F1 helmet, glasses, whatever)

Critical: Same head tilt. Same shoulder angle. Same lighting direction.

If the AI gives you different poses, regenerate until it matches. Or take a screenshot of your first image and use it as reference for the second.

Step 4: The Claude Prompt

Drop this into Claude Opus 4.6. Replace the bracketed parts.

```
Create a personal portfolio landing page for [YOUR NAME] built as a single full-screen hero that occupies the entire viewport. Use a large portrait image [BASE IMAGE URL] as the background, centered and scaled to cover the screen. Place my name in the top-left corner in an elegant serif font such as Playfair Display, with the first and last name stacked on separate lines. In the top-right corner, add a simple navigation link labeled 'ABOUT'.

In the bottom-right corner, include links to [TWITTER, GITHUB, LINKEDIN] using solid, filled SVG icons so they remain clearly visible and easy to recognize. Each icon should link to the appropriate social profile.

The primary interaction should be a circular highlight cursor that follows the mouse smoothly with a slight delay. This round spotlight acts as a reveal mask, exposing a second version of the portrait [VARIANT IMAGE WITH HELMET] beneath the main image. As the user moves the cursor, it should feel like they are scanning across an alternate layer of the photo.

When the cursor moves faster, the circular highlight should leave behind soft, fading echoes that quickly dissolve, adding motion and responsiveness. In the background, add a subtle animated grid pattern that gently reacts to cursor movement, creating depth while staying understated.

All text elements, including the name, the "ABOUT" link, and the website icons, should dynamically invert to white when the circular highlight passes over them to maintain contrast. Use smooth transitions of around 300ms. Apply a light parallax effect where elements shift slightly opposite to cursor movement. The overall look should remain minimal and refined, with a clean white base and the imagery and interaction as the visual centerpiece.
```

That's it. You get a portfolio page that looks like you paid a designer $3,000.

THE FIX (WHEN IMAGES DON'T ALIGN)

Sometimes the helmet version is slightly shifted. The reveal effect looks off.

What I did: Take a screenshot of the first image. Ask AI Studio to "generate the same exact person, same exact position, wearing [helmet/astronaut helmet/F1 helmet]." Paste the screenshot as reference.

Regenerate until alignment matches.

LINKS

→ AI Studio: https://aistudio.google.com/
→ WaveSpeed AI : https://wavespeed.ai/

Until next week,
@speedy_devv

Keep Reading