> ## Content Index
> Fetch the complete content index at: https://mitchellens.ink/llms.txt
> Use this file to discover other available public pages before exploring further.

# Closer #024
- URL: https://mitchellens.ink/closer/024/
- Published: 2025-09-17T18:00:23.000Z
- Updated: 2025-10-06T14:31:08.000Z
- Description: The soul of an image can not and will not be generated by computers. Humans create human experiences. Humans connect to human experiences. Computers are mimicking that very closely, but you can always tell.
- Author: Mitchel Lensink
- Tags: Closer, Field

SPONSORED 

This weekly experiment is on an indefinite hold, until significant AI-advancements have been made.  
  
Curious about the conclusions? Read [Photography in the Age of AI (2025): Lessons From 25 Weeks of Experimentation](https://mitchellens.ink/closer/photography-in-the-age-of-ai/)

[Read now ](https://mitchellens.ink/closer/photography-in-the-age-of-ai/) 

Welcome to Closer,

A weekly experiment in AI interpretation: I share a photo, ask AI to describe it, then generate an image from that description. This is edition #024\. Prompts are in grey boxes. *Descriptions are in italics*.

Continuing in last week's spirit of sharing images from personal projects I like a lot, this final *regular* entry into Closer is shot during [my first long(er) distance walk: the Grebbelinie](https://mitchellens.ink/walking/grebbeliniepad/). This photograph is taken while standing on the Liniedijk, just outside Leusden.

## LLM models used

**GPT-5 Auto** for image interpretation, and image generation.

## The input

✍️

Please describe the attached image as well as you can. Don't skimp out on details and make sure you will be able to understand what's in the image when you read the description. You need to be able to form a mental picture of the image, without actually seeing it.

![The image shared with ChatGPT as input.](https://storage.ghost.io/c/8a/15/8a1564aa-a008-4e21-8398-12d04de07fcb/content/images/2025/09/012_Mitchel-Lensink_210909_Netherlands-Grebbeliniepad-1.jpg)

The image shared with ChatGPT as input.

## The output

*The image depicts a rural scene with traditional brick farm buildings and some large wooden cable reels in the foreground.*

*At the center-left stands a main barn-like structure made of red brick with a steep, tiled gable roof. The roof tiles are weathered, with patches of moss or discoloration. The facade of this building has several arched windows and doors: two black wooden doors at ground level, one larger and one smaller, and three small windows arranged symmetrically above. One of the higher windows has a green wooden shutter. The brickwork around the openings features decorative arches, enhancing the rustic charm of the building.*

*Behind this main structure, slightly to the right, is another red brick building with a similar tiled roof, but it appears more like a farmhouse. Attached to or rising above it is a smaller, weathered wooden structure, almost like a tower or ventilated loft, with a corrugated roof — possibly used for storage or as a dovecote.*

*In the foreground, on the grassy verge by the road, lie several large wooden cable reels. These are industrial-sized spools, weathered from use, with the circular ends showing stains, cracks, and holes. Some are upright, while others are tilted or resting at an angle. One of them has a blue sticker or piece of tape still attached. They add a sense of scale and a contrast between industrial utility and the rustic farm environment.*

*To the right, a tall leafy tree dominates the edge of the frame, its green foliage casting shade over part of the ground. The road running between the reels and the buildings appears unpaved or lightly surfaced, typical of a rural setting.*

*The overall atmosphere is calm, with muted earthy colors — browns, reds, greens — and soft daylight that suggests a clear sky with light cloud cover. The scene feels like a quiet countryside location, slightly industrial but mostly agricultural, with a mix of traditional farming architecture and leftover construction materials.*

✍️

Generate an image with an aspect ratio of 3:2 based on this description: {**the description previously generated*}

![The image generated by ChatGPT based on its description of my image alone.](https://storage.ghost.io/c/8a/15/8a1564aa-a008-4e21-8398-12d04de07fcb/content/images/2025/09/ChatGPT-Image-Sep-12--2025-at-10_30_48-AM-Large.jpeg)

The image generated by ChatGPT based on its description of my image alone.

## Impressions

I'm continuing to be impressed with the accuracy with which AI is able to correctly identify elements of an image, and then also correctly identity what those elements actually are. When I read "*several large wooden cable reels. These are industrial-sized spools, weathered from use, with the circular ends showing stains, cracks, and holes,*" I was pleasantly surprised by the semantic understanding the technology has of our world.

The image generation is... functional. The scene described is depicted to the point that you can definitely see the inspiration. Both images, real-life and AI, convey the same information. AI just does so in a much more clinical way. It's how I would paint the scene (provided I could paint) if I had only the description at my disposal. As I said previously: it's nice, but it's fake. It looks fake. It *feels* fake. So, in all honesty, if you have a use case where being 'real' is not essential (i.e. the image is merely illustrative) the image *could* fulfill the same role. It's functional.

Reasoning from the perspective of an artist, this tool will not replace me. I am not trying to show you a picture of a barn with some spools in front of it. Although that's what it *is*, that's not the *goal*. Instead, I am trying to show you what walking the *Grebbeliniepad* looks like. How it feels to be out there. What you might come across if you do the same walk. I am conveying an experience through my images. For that, I need the images to be real, imperfect, slightly limited by the light available during my walk. Because you will experience the same.

Take all that real work to achieve that photo out of the equation, skipping straight to the photo-making part, and you remove all the soul and the ability to connect to it on a human level.

Thanks again for following along, see you next week. For the last time.

Mitch

****Got a minute?** I’d love your quick thoughts — 3 multiple choice questions, that’s it.

[Share feedback ](https://tally.so/r/3102AW)