Friday's Photo: My Grandmother's Photo was NOT Restored by AI

In June, I set out to repair a badly damaged photograph of my grandmother, Myrtie Hairston Bryan. I uploaded the image to ChatGPT and asked it to restore the photo without altering the original coloring or her facial features. The result looked promising, and feeling satisfied, I labeled it “restored” and proudly shared it on my blog. My enthusiasm had been sparked after listening to Episode 25 of The Family History AI Show with Mark Thompson and Steve Little—though, in hindsight, I clearly missed an important point.

Restoration or Reconstruction? 

When I first ran my grandmother’s photo through Artificial Intelligence (AI), I thought I was seeing a careful repair job. The scratches and spots vanished, and her face appeared smoother and clearer than before. Only later did I realize the AI hadn’t really fixed the original image at all—it had recreated it.

AI studied the damaged image and generated new pixels to replace the missing details. The end result certainly looked like my grandmother, but it wasn’t the same photograph she carried home from the studio in the early 1900s. It was a modern, computer-generated version of that moment.

This difference matters. Just as we distinguish between an exact transcription and a “cleaned up” version of a document, we should be clear about whether a picture shows original evidence or an interpretation.

When we use AI to “improve” old photographs—whether by sharpening, recoloring, or filling in missing areas—we’re creating a new version. Those images should be clearly labeled, and the unaltered scan should always remain the authoritative copy. 

Moving Forward with AI 

I have removed the June 20th post because I don’t want someone to see that recreated image and upload it as a true restoration to sites such as Ancestry, where it would be copied and shared repeatedly.

I still appreciate what AI can do. It’s a tool I use daily for a wide range of tasks, including genealogy. However, when it comes to photographs, I’ll be much more cautious and look forward to the day when AI can truly repair a historical image rather than rebuild it.

My thinking about AI and photos has been shaped in part by conversations in the genealogy community—especially discussions from The Family History AI Show with Mark Thompson and Steve Little.

If you want to know more about the families I research, click here to like my Facebook page, where you will see each post and other genealogical finds. 

Diana

© 2025

Sources

“Episode 25: AI Image Generation Advances,” The Family History AI Show, (https://podcasts.apple.com/us/podcast/ep25-chatgpt-4o-transforms-image-generation-jarrett/id1749873836?i=1000712214261accessed 21 October 2025).

“Episode 27: Restoration or Recreation?” The Family History AI Show, (https://podcasts.apple.com/us/podcast/ep27-ai-image-restoration-concerns-perplexitys-future/id1749873836?i=1000717145783: accessed 21 October 2025).

Friday's Photo: Second-Great-Grandparents

William Moore Criswell and Mary Ann Evans Criswell

Second great-grandparents are ideal for genealogy research. Some vital records and census data usually exist for them. I have found marriage licenses, census records, a few birth records, directories, newspaper articles, and so much more! And even though they all were born between 1793 and 1850, I have photos of six of them.  

Julia Harvey Glynn and 
daughter, Carrie

Everyone has 16 second great-grandparents. Each generation back doubles the number of direct ancestors: 2 parents, 4 grandparents, 8 great-grandparents, and 16 second great-grandparents. Of my 16 second great-grandparents, I know the first and last names of eleven. 

Olive Caroline Davis

The names of three of my maternal second great-grandparents are unknown. The remaining are listed below:

Olive Caroline Davis

George Lullen Giddens and Luellen Bradshaw

Joseph Allen Glynn and Julia Harvey

My paternal second great-grandparents include the following, along with one unknown second great-grandmother:

Reddick Bryan and Elizabeth Span Regan

William Moore Criswell and Mary Ann Evans

Peter Albritton and Hollon (last name unknown)

John L. Hairston  

 

Reddick Bryan and Elizabeth Span Regan Bryan

Five of my second great-grandparents are still a mystery to me. But each blank spot on my tree is a reminder that the search is never really over. How many of your 16 can you name?

If you want to know more about the families I research, click here to like my Facebook page, where you will see each post and other genealogical finds. 

Diana

© 2025

Carrie Glynn and Julia Harvey Glynn, photograph, ca. 1885; scanned image, held in the photo collection of Diana Quinn, Virginia Beach, VA, 2025. Location of the original photo is unknown. 

Mary Ann Evans, photograph, no date; scanned image, from the privately held photo collection of Diana Bryan Quinn, Virginia Beach, VA, 2025. 

Olive Caroline Davis, photograph, no date; scanned image, from the privately held photo collection of Brenda and Mike Parker, 2001.

Reddick Bryan and Elizabeth S. Regan, photograph, abt 1855; scanned image, from the privately held photo collection of Diana Bryan Quinn, Virginia Beach, VA, 2025. 

William M. Criswell, photograph, no date; scanned image, from the privately held photo collection of Lena Stone Criswell, NM, 2001.

Friday's Photo: May Wright and Bella Along With Baby, Palma Jean Clark

This was one of those photos I thought would be easy to research, but not so much. 

The baby is Palma Jean Clark, daughter of Marguerite Cook and her husband, Albert Clark of Bienville Parish, Louisiana. Palma was born on 20 March 1936. I first met her [Palma C. Beckett] in 2014 when she graciously allowed me to go through her mother's genealogy files. After learning she had hundreds of old photos, I made the 1,800-mile trip to her home in Texas two more times. 

It appears that Marguerite Cook Clark wrote on the back of the photo. Note that the following is a transcription of a handwritten note from 1936. It includes terminology that was commonly used at the time but is now considered outdated and inappropriate. I’ve preserved the original wording for historical accuracy and context.

Palma Jean Clark
1936-2023

This is 2 mo. The colored friends are working for gramma. You should have seen the pink roses in the background . . . The rest is not legible as parts are torn away. Later, someone wrote the following:

Mae Wright 

Bella 

with Pal 

at 2 months.

 

In 1936, both of Marguerite’s grandmothers were living in Bienville Parish. Her paternal grandmother was Sophronia Pauline Porter Cook, and her maternal grandmother was Laura Frances Bryan Martin. 

Unfortunately, Mae Wright and Bella could not be identified. There were several Wright families in Bienville Parish and the surrounding areas, so I am hoping someone recognizes them as family when I post to the Bienville Parish Facebook groups. 

If you want to know more about the families I research, click here to like my Facebook page, where you will see each post and other genealogical finds. 

Diana

© 2025

Diana Quinn, #1 Diana's Bryan-Quinn Family, Ancestry.com (https://www.ancestry.com/family-tree/tree/45260559?cfpid=6334928766: accessed 6 July 2025).

May Wright and Bella, Along With Baby, Palma Jean Clark, photograph, 1936; digital images, from the privately held photo collection of Marguerite Cook Clark (1913-1989), Waynesville, North Carolina, 2025. Photos were accessed and scanned at the home of Marguerite Cook Clark's daughter in Alpine, Texas, on April 28, 2014, September 14, 2014, and November 9 to 11, 2016.

Friday's Photo: Wayne Wimberly Martin (1922–1954)

Wayne Wimberly Martin was born in Ringgold in Bienville Parish, Louisiana, on July 10, 1922. The son of Thomas Jefferson Martin, Jr., and Willie Bessie Murph Woodard, he was affectionately known as “Preacher” for his deep knowledge of the Bible. Wayne passed away on October 16, 1954, in a car accident. He is buried at Wimberly Cemetery in Bienville Parish, Louisiana.

If you want to know more about the families I research, click here to like my Facebook page, where you will see each post and other genealogical finds. 

Diana

© 2024 

Photos of Wayne Wimberly Martin, photograph, n.d.; scanned image, from the privately held photo collection of Mary V. Smith, Alaska, 2004; original images photographed between 1973 and 1993.

Vera Meeks Wimberly, Wimberly Family History, Ancestors, Relatives, and Descendants of William Wimberly, Pioneer from Georgia to Louisiana 1837 (Houston Texas: D. Anderson, 1979), page 320.

Friday's Photo: Uncle Tom White

Z. Thomas White, known as "Uncle Tom White," was born on 29 October 1869, likely in Bienville Parish, Louisiana. He died on 10 July 1956 in Caddo Parish and is buried at Mount Olive Cemetery in Bienville Parish. His gravestone reads “Uncle Tom White,” matching the name on the photo.

He was one of nine children of Philemon White and Mylydia McGee White, who settled in Bienville Parish before the Civil War. The name “Uncle Tom” may have come naturally, as he had many nieces and nephews through his eight siblings. Tom never married and appears in census records living with his parents and later with his brother, David M. White.

Records list him variously as Z. Thomas White, Zae T. White, Tom Z. White, Zacarier Thomas White, Ezekiel White, Zac White, and Zackhry Thomas White. 

This photo came from Mary V. Smith's collection. She wrote that Niler [Nila] Sledge Edwards gave her mother, Anna Laura Martin, the family photo album of Henry Collin Sledge of Bienville Parish. Mary also wrote that she copied the names as found on the photos. 

If you want to know more about the families I research, click here to like my Facebook page, where you will see each post and other genealogical finds. 

Diana

© 2025

Billie Jean Poland, History of Bienville Parish, Vol. IIhe  (Bossier City, Louisiana: Everett Companies, 1990), p. 798-799, images 808–809; digitized at Bienville Parish Library Digital Archives (https://bienville.advantage-preservation.com : accessed 22 May 2025).

"Tom/Thomas White" search, Ancestry.com (https://www.ancestry.com : accessed 22 May 2025), search results for “Tom/Thomas White,” born 1869, Bienville Parish, Louisiana; results included entries from U.S. Census Records, Louisiana Statewide Death Index, 1819–1964, Find a Grave Index, and Public Member Trees.

"Uncle Tom White," photograph, n.d.; scanned image, from the privately held photo collection of Mary V. Smith, Alaska, 2004; original images photographed between 1973 and 1993.

Friday's Photo: Putney, Vermont

Said to be Vermont's oldest General Store, the history of this store goes
back to 1796 - see more at Putney General Store.

In the 1980s, before I developed an interest in genealogy, I was focused on traveling and furnishing my new home with antiques collected along the way. A trip to New England in 1984 perfectly aligned with those interests. During that trip, I managed to fit in one brief family history stop: a visit to Putney, a small town in Windham County, Vermont. At the time, all I knew was that someone on my mother’s side had once lived there.

Mary Lucy Glynn

After years of research, I know just how significant Putney is to my family history. My fourth great-grandparents, Benjamin Reed and Huldah Pratt, lived there and are buried in the town. Their daughter and my third-great-grandmother, Nancy Reed, wife of Joseph T. Glynn, is also buried in a local cemetery, along with my second-great-grandfather, Albert Joseph Glynn. My great-grandmother, Mary Lucy Glynn—who married Charles Giddens—was born in Putney. 

Now, a return trip to Vermont is at the top of my wish list. This time, I plan to visit the cemeteries where my ancestors are buried and spend time in local archives to dig deeper into my family history.

If you want to know more about the families  I research, click here to like my Facebook page, where you will see each post and other genealogical finds. 

Diana

© 2025

"Putney, Vermont abt 1984" and "Mary Lucy Glynn," photographs; scanned images, original photograph from the privately-held collection of Diana Bryan Quinn, Virginia Beach, VA, 2025.

Friday's Photo: The Thompson Brothers of Erath County An AI Fail

After comparing my father's photos with those of his brother's in Tuesday’s post, Buster vs. Dad – An AI Perspective, I’ve found myself on a new mission—revisiting my collection of unidentified photos with help from AI.

This photo of two young men was shared by a cousin, who identified them as Floyd William Thompson (1889-1968) and one of his brothers. 

Floyd had five brothers:

• Aaron Whitney Thompson (1886-1964)
• Claud Clarence Thompson (1891-?)
• Edgar Richard Thompson (1896-1983)
• Walter Alexander Chisum (1876-1816) [half-brother]
• Philip Louis Chisum (1881-1962) [half-brother]

I uploaded the photo to OpenAI’s ChatGPT along with at least one confirmed image of each brother—except Claud. I’ve never come across a photo of Claud Thompson. I also provided their names and birth years. I've learned that AI performs better when I include some background information. 

AI Analysis

I first used ChatGPT 4o to upload photos and ask questions. I really liked this table created by AI. It made me consider details I might have overlooked. 

This model confidently identified Floyd as the standing figure, citing specific facial features and stance as evidence.

However, this AI automatically assumed the standing boy was older, despite the possibility to the contrary. It also made questionable observations, like claiming the seated boy had "less prominent ears"—which contradicts what's visible in the photograph. 

When I challenged certain conclusions, the AI adjusted its analysis to accommodate my input rather than defending its position with evidence. For example: 

• With the initial comparison, AI wrote, "The seated boy is likely another Thompson brother, but doesn't clearly resemble Edd, nor Floyd in his later years."

• When discussing birth years, AI responded, "Based on appearance, Claud Clarence Thompson (b. 1891) is a more likely candidate than Aaron."

• When reminded that no photos of Claud existed for comparison, the AI response was "The seated boy now appears to be Edgar Richard Thompson rather than Claud."

This inconsistency prompted me to seek a second opinion from a custom GPT specializing in historical photo analysis, Mark Thompson’s Historical Photo Analyzer, available through OpenAI’s ChatGPT platform. This consultation provided excellent historical context and thorough comparative analysis, but yielded the exact opposite conclusion, identifying Floyd as the seated brother.

Conclusions

Given the conflicting results, I decided it was best to conclude this AI comparison. Moving forward, I'll continue using AI as a supplemental tool. In my last post, Buster vs. Dad – An AI Perspective, AI did an excellent job pointing out similar features that could be easily observed. Not so much with this project. What I learned is that AI can help me see things I might overlook, but it is not a replacement for my intuition, family knowledge, or careful comparisons. 

For now, I will share this post with my family and on the Erath County Genealogical Society Facebook page, in the hope of gaining more insight from others who might recognize the faces or have additional knowledge about this family. 

If you'd like to learn more about the families I research, click here to follow my Facebook page, where you can view each post and other genealogical discoveries. 

Diana

© 2025

ChatGPT, "Comparison and Identification of Floyd Thompson in Historical Photo; Analysis of Seated vs. Standing Boy," OpenAI (https://chat.openai.com : accessed 25 April 2025).

Mark Thompson’s Historical Photo Analyzer (GPT : ChatGPT, OpenAI), "Historical photo analysis customized for detailed image study and genealogy insights," analysis provided to user DB Quinn, 25 April 2025; privately held by DB Quinn, VA.

Thompson Family Photographs, digital images, privately held by DB Quinn, Virginia Beach, VA, 2025; scanned from original photographs shared with DB Quinn in 2001 by Juanita Gleghorn, Tom Thompson, and Nadine Waugh during a visit to Texas.

Buster vs. Dad – An AI Perspective

Buster and Dad in their early teens. 

I decided to use AI to help identify some of my unknown family photos. The first few results weren’t great—a boy was labeled as a girl, another as a man, a scratch was mistaken for a clothesline, and an attempt to create a collage ended with images that didn’t look like my family at all. But when I started using OpenAI’s ChatGPT to compare photos side by side, I finally began to get useful results.

Buster or Dad?

I have several children in photos that have always been in question—were they my father or his brother? My cousin, who originally had the photo collection, labeled all of them as “Buster.” Buster was my dad’s older brother, Hairston Albritton Bryan, born in 1906. My father, Whit Criswell Bryan, was born in 1920. While I’d already guessed that some of the photos were of Dad, there was always a bit of doubt. AI helped confirm what I’d suspected.

I started by uploading one of the questionable photos and simply asked, “Can you date this?”

AI responded with an analysis of the child’s clothing, shoes, and the overall photographic style—pointing out the sepia tone and the formal studio setup. Based on these features, the photo was dated to somewhere between 1910 and 1920.

I followed up with: “This has been identified as my Uncle Buster, who was born in 1906, but could it actually be my father, born in 1920?”

The response was clear:

“While it could be your father, the styling strongly favors your Uncle Buster (born 1906). Everything about the child’s appearance, the clothing, and the studio portrait setup points to the 1910–1912 range.”

I decided to go a step further. I uploaded another photo and asked, “Could this be the same child?”

AI responded by analyzing the clothing, backdrop, and photo mount, estimating a time frame of circa 1910-1912, which lines up closely with Buster’s childhood years.

It noted that both children had oval-shaped faces, strong jawlines, and similar eye placement and spacing. The resemblance was plausible, especially when considering age progression, fashion trends, and the photographic style. If the child in both photos was Buster, the timeline worked.

Next, I shared teen photos of Buster to see if there was a visible connection. AI noted strong continuity in features—especially eye shape, nose, and jawline—linking the child in the earlier photos to the teen in the later ones.

I added this photo and asked, “What do you think of this photo of my father—Buster’s younger brother, born in 1920? My cousin said it was Buster, but I know it’s Dad.” 

AI responded with, "The boy is dressed in a classic sailor suit with a wide collar and checkered tie, a style popular from 1915 to the early 1930s. His dark stockings and leather shoes complete the look. His straight, bowl-style haircut with a trimmed fringe was typical for boys in the early 1920s, especially before school age. Based on these details, the image likely dates to around 1923–1925, which fits perfectly for your father, born in 1920."

So I shared three known childhood photos of my father, and AI came back with, "These known photos of your father clearly show a consistent progression from babyhood to adolescence, with strong physical matches to the sailor-suit portrait. Between the features and the timeline, it’s very safe to say the child in the sailor suit is your father—not Buster."

I shared three more photos, thought to be of Dad or Buster, and received the expected results.  

Dad - Whit Criswell Bryan

Buster's Baby Photo
Dad on a Donkey

Comparing Tools and Doing My Own Research

All of the photo analysis and comparisons in this article were generated using OpenAI’s ChatGPT. I also tried Anthropic’s Claude. Claude was more cautious. It provided similar comparisons of facial features and timelines, but was less willing to commit—recommending a second look and suggesting I talk to family members. 

And while ChatGPT provided useful insights, I didn’t accept everything without question. I did my own research to confirm the clothing and hairstyle information, especially since sources weren’t cited. After conducting my own research, I generally agreed with ChatGPT’s timelines for hairstyles and clothing; however, the sources I found indicated that these trends didn’t follow strict cutoffs—there was more overlap and variation than the AI responses suggested.

Final Thoughts

This process was a good reminder of the value of revisiting old photos with new tools and a fresh perspective. AI won’t solve every mystery, but in this case, it helped me ask better questions and, more importantly, confirm what I’d long suspected.

If you want to know more about the families I research, click here to like my Facebook page, where you will see each post and other genealogical finds. 

Diana

© 2025

Sources

Edward Zapletal, Publisher and Editor, More Dating Old Photographs 1840-1929 (Toronto: Moorshead Publishing, 2011).

Historic Boys' Clothing, "United States Sailor Suits: The 1920s," web page, Historic Boys' Clothing (https://histclo.com/style/suit/sailor/sailorus20.html : accessed 22 April 2025).

Jo B. Paoletti, “Clothing and Gender in America: Children’s Fashions, 1890-1920.” Signs 13, no. 1 (1987): 136–43 (http://www.jstor.org/stable/3174031: accessed 14 April 2025). 

Maryanne Dolan, Vintage Clothing 1880-1980 (Alabama: Books Americana Inc., 1995).  

Special Collections at the Richardson-Sloane Special Collections Center, "Saluting the Sailor Suit," blog entry, 2 July 2022, Primary Selections from Special Collections, blog (https://blogs.davenportlibrary.com/sc/2022/07/02/saluting-the-sailor-suit/ : accessed 22 April 2025).

TPR, "The Bowl Haircut," blog entry, 2 January 2020, The Past Recedes, blog (https://tpr76797.wordpress.com/2020/01/02/the-bowl-haircut/ : accessed 22 April 2025).

From Loyalists to Free People of Color: Stories You Don’t Want to Miss!

You Don’t Have to Live in Virginia Beach to Attend Genealogy Day at the Beach!

Every spring, I look forward to highlighting this event hosted by one of my favorite groups, the Virginia Beach Genealogical Society. Genealogy Day at the Beach is right around the corner—Saturday, April 19, 2025—and this year’s event is shaping up to be one of our best yet. Hosted by the Virginia Beach Genealogical Society and the Virginia Beach Public Library, it’s a day filled with inspiration, learning, and community connections.

But here’s the best part: you don’t have to be in Virginia Beach to join us—and there’s no cost! This event is hybrid, meaning all speaker presentations are available both in person and via Zoom. No matter where you are, you can tune in and enjoy a remarkable lineup of genealogical speakers.

Registering for Zoom access is free, and you’ll find the Zoom links posted on the Virginia Beach Genealogical Society website on the day of the event.

So spread the word! Invite your genealogy friends and make a day of it. You don’t have to live in Virginia Beach to enjoy this incredible lineup of speakers. But if you're local, we would love to see you in person! There's nothing quite like sharing the day with a friendly, enthusiastic group of people who are just as passionate about genealogy as you are. Whether you're into DNA, colonial history, African American research, or family mysteries, you'll find someone here who shares your interests.

Come learn, connect, and get inspired! 

If you want to know more about the families I research, click here to like my Facebook page, where you will see each post and other genealogical finds. 

Diana

© 2025