AI images have become scary good.

You type a prompt.

ChatGPT gives you a poster, product shot, ad visual, character, thumbnail, whatever.

First reaction:

Then you ask for one small change.

Make the logo smaller.

Fix the text.

Change the background.

Make it more premium.

Suddenly the image gets worse. This is where most people get trapped.

They keep prompting. The image keeps drifting.

And after 20 minutes, the first version was somehow better.

Contra Labs tested this with designers.

They ran 42 design sessions with 7 designers using ChatGPT Images 2.0.

Only 5 out of 42 sessions produced an image that shipped directly from ChatGPT.

Some images became client-presentable, but most still needed Photoshop, Illustrator, or Figma before final delivery.

That is the useful part of the study.

ChatGPT Images is strong.

But designers are not using it as the whole design stack.

I am Alex, welcome to ShortCu8 by Innov8.

Lets Dive Deep 🐰

Use ChatGPT Images like a designer.

The designer workflow is simple:

ChatGPT helps you escape the blank canvas.

Your design tools help you ship the final image.

Contra Labs ran a study on ChatGPT Images 2.0 with designers.

They tested 42 design sessions across 7 designers.

The question was simple:

The answer:

Kind of.

But not fully.

Their study found:

So the lesson is not:

The real lesson is:

That is exactly how designers are using it now.

Use this simple rule.

Edit 1: Generate the first concept

Ask for the main visual.

Give it the subject, style, mood, use case, and layout.

Edit 2: Fix the big direction

Change background, composition, lighting, angle, or vibe.

Big edits are still fine here.

Edit 3: Stop and move

If you are now asking for:

stop prompting.

Move to Figma, Photoshop, or Illustrator.

That is the designer move.

Most people make this mistake:

This usually creates bad text and random logo placement.

Try this instead:

See the difference?

You are asking it to create the visual base.

Then you add the real text and logo in Figma.

Use it for:

It is fast when you need direction.

It is useful when you do not know what the image should look like yet.

It gives you options quickly.

That is the power.

Do not waste too much time making it handle:

It can sometimes do these.

But if you need it to be correct, use the proper tool.

Prompting is not always the fastest path.

Sometimes the fastest path is moving the file to Figma and fixing it yourself.

Next time you make an AI image, do this:

That is how you avoid edit hell.

Now Top Designers using AI to get momentum.

Then they use design tools to make it shippable.

That is the shortcut.

Know when to prompt. Know when to stop.

Now go create something new.

We read every reply - just reply to this email and let us know how we can improve !

#AD1

Most AI tools ask you to trade your data for intelligence. Norton Neo doesn't. It's the first safe AI-native browser built by Norton, and it gives you powerful built-in AI without handing your privacy over to get it. Search, summarize, and write with AI built directly into your browser. Your data stays yours. Your context stays private.

Built-in VPN, anti-fingerprinting, and ad blocking come standard. No add-ons. No setup. No compromises.

Fast. Safe. Intelligent. That's Neo.

Download Norton Neo

#AD2

Every ai app hits the same wall: the agent needs to remember something, store something, try something. Ghost is postgres built for that. Spin one up per agent. Fork it. Throw it away. Pay nothing when it sits idle.

Unlimited Postgres, Free