ChatGPT Images 2.0 for Genealogy: Photo Enhancement

ChatGPT Images 2.0 enhances old family photos with AI

​ChatGPT Images 2.0: A New Era for Visual Genealogy (and My First Tests with Photo Enhancement)

On April 21, 2026, OpenAI released a major update to its image generation capabilities: ChatGPT Images 2.0.

This isn’t just a minor improvement, it's a significant step forward in how artificial intelligence can create, transform, and interpret images. In OpenAI’s own words, this is:
“a state-of-the-art model that can take on complex visual tasks and produce precise, immediately usable        visuals… our first image model with thinking capabilities.”

As someone who regularly explores how AI can be applied to genealogy, I wanted to test this new tool right away. Over the first few days, I experimented with quite a few of its features, but one stood out immediately for its practical use:
Enhancing old photographs.
​
Before diving into my results, let’s take a look at what this new tool actually offers.

​What Is ChatGPT Images 2.0?

ChatGPT Images 2.0 is a built-in image creation and transformation tool inside ChatGPT. After clicking “Create an image,” you can either write your own prompt or select from the “Explore ideas” feature, which is a list of instant, one-click creative options, which I used.​
As of now, those include:

• Enhance Photos
• Fix Lighting
• Studio Headshots
• Anime
• Comic
• Blueprint Poster
• Infographic Poster
• Interior Design
• Color Analysis
• 3D Avatar
• And many more (with new options already being added)

​Key Capabilities (and Why They Matter for Genealogy)

What makes Images 2.0 different isn’t just what it can create, but how well it understands what you’re trying to do.
​Looking through the examples on the OpenAI blog, here's what really stood out to me:
1. "Thinking" Capabilities
This is the first image model from OpenAI with reasoning abilities.
That means it doesn’t just generate visuals, it also, for the most part, understands what you're trying to do.
For genealogists, this means:

• Smarter visual storytelling
• Better reconstruction of historical context
• More accurate transformations of existing materials

2. More Realistic Images
Looking through the examples on the OpenAI blog, I saw that the new model can generate pretty realistic images in a wide range of styles, including:

• Candid snapshots
• Gritty cinematic realism
• Vintage-style photography
• Disposable camera aesthetics

3. Different Styles You Can Use
I also learned that you could even create:

• Japanese manga
• Comic styles
• Movie posters
• Character sheets
• and more

(This is something I’ll be covering in a future post because it deserves its own deep dive.)

4. Better Text in Images
One of the biggest improvements:
Text inside images is now actually readable and usable.
This is a huge step forward for:

• Infographics
• Educational materials
• Presentation slides
• Social media graphics

5. Works in Different Sizes and Layouts
Whether it’s:

• A panoramic image
• A vertical social media post
• A structured infographic

…the tool seems to adapt while keeping everything balanced.

6. Smarter Visuals and Ideas
It can now handle more complex ideas, such as:

• Infographics
• Diagrams
• Visual explanations

7. Ready to Use
This is where things get really interesting.
This feels like something meant to be used in real, everyday situations, which I will definitely be trying next:

• Marketing and advertising
• Educational content
• Website visuals
• Social media graphics

For genealogists, this means:
less time creating those visuals manually and more time focusing on research and storytelling.

​My First Tests: Enhancing Historical Photos

I wanted to start with something practical and useful right away:
Enhancing old family photographs.

​Test 1: 2nd Great Grandparents Family Photo

​On the first day of its release, I tested a photograph of my 2nd great grandparents and their family (including my great grandfather).
Results:

• Significant improvement in clarity
• Scratches, creases, and damage removed
• Overall image looked cleaner and more usable

However:

• Mouths were slightly altered across individuals
• My 2nd great grandmother’s eyes changed noticeably
  • Her original expression was very distinct, but it was softened
• Lace detail at the bottom of her dress was removed
  • Likely mistaken for damage due to how faint it was

Takeaway:
A fantastic enhancement overall but of course not a perfect preservation of every original detail.

ChatGPT Images 2.0 Enhance Photos- Example 1

​Test 2: Great Grandparents Photo

Another strong result:

• Clear improvement in image quality
• Cleaner, sharper presentation

Consistent issue:

• Slight changes to the eyes and expression

And as any genealogist knows:
The eyes, and their expression, are everything in a photograph.

ChatGPT Images 2.0 Enhance Photos- Example 2

​Test 3: 6th Grade Friendship-Size Photo

​This was a much smaller, lower-quality image I tried.
Result:

• Impressive clarity improvement
• But:
  • Lips were slightly altered
  • Eye expression changed enough that it just didn’t quite feel like me 

ChatGPT Images 2.0 Enhance Photos- Example 3

​Test 4: 2nd Grade Wallet Photo

​This one was the most accurate.
Result:

• Very close to the original
• Minimal changes
• Expression remained largely intact
• ​I still saw myself

ChatGPT Images 2.0 Enhance Photos- Example 4

​Overall Thoughts on Photo Enhancement

This tool is extremely promising and already useful.
But it’s important to understand what it is (and isn’t):
What It Does Well

• Repairs damage (scratches, folds, wear)
• Improves clarity and sharpness
• Enhances overall usability of old photos

Where It Still Needs Improvement

• Subtle facial changes (especially eyes and expressions)
• Occasional loss of fine details
• Interpretation vs. preservation balance 

​Important Reminder for Genealogists

This is where I want to be very clear:
This tool enhances, but it also interprets.
In other words, it is still creating parts of the image.
For genealogical use:

• Always keep the original image
• Treat enhanced versions as visual aids, not replacements, and label them as such
• Be cautious when using enhanced images as evidence 

​Final Thoughts

This is definitely a huge step up from before.
We're moving from:

• AI as a novelty

to:

• AI as a practical, everyday tool for genealogists

The photo enhancement feature alone is already valuable and it can only improve from here.
And this is just one of its new capabilities.
In future posts, I’ll be exploring other uses I saw on the OpenAI blog:

• Artistic transformations (anime, comic, etc.)
• Visual storytelling for genealogy
• Business and content creation uses
• Presentation and educational applications

Because if these first tests are any clue…
We’re just getting started.

​More AI and Genealogy

Learn about more AI in Genealogy updates, tips, and resources (including photo tools), along with other family history and genealogy resources under the AI in Genealogy and  Genealogy Resources categories and on my dedicated Genealogy Resources page.