Closer

Closer #003

I purposely chose to share a relatively complex black and white image with ChatGPT for this week's entry. Lots of layers and many things going on in the frame. The black and white edit also provides the AI with less context. How does it perform?

Mitchel Lensink
Apr 23, 2025
4 min read
The image shared with ChatGPT as input.

Welcome to Closer,

a weekly newsletter where I take one of my photos, ask AI to describe it, then see what kind of image it can generate from its own description—an ongoing experiment in the capabilities of AI, and what that means for humans. This is edition #003.

A thought I had: it seems progress isn't linearly moving towards something but it's circularly repeating similar processes that take on different forms that build on top of what's come before and now achieving the same things but differently, though perhaps not inherently better. Is AI the modern-day industrial evolution?

As always it goes: input image & prompt to describe → AI's description of that image → AI generated image → some of my first impressions. Prompts are in the grey callout boxes, the AI description is cursive.

LLM models used

GPT-4-turbo for image interpretation. DALL·E 3 for 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.
The image shared with ChatGPT as input.

The output

This black-and-white photograph appears to be taken through a window or a transparent panel on a rainy day. The surface of this glass (or perhaps clear plastic) in the immediate foreground is covered in numerous raindrops and rivulets of water, which stand out sharply and form distinct vertical lines or streaks. The drops catch the light differently, creating points of brightness and shadow along their contours, and serve as the primary in-focus detail.

Beyond the wet, spotted surface, the scene itself is somewhat blurred or out of focus, giving the background a soft, diffused look. From what can be made out, the setting appears to be an outdoor gathering—possibly a festival or fair. There are white tents or canopies set up, and at least one large, legible sign that reads “PASTA” in capital letters toward the upper right portion of the image. A few other circular or oval signs hang nearby, but their text or symbols are less distinct.

A loose row of people is walking from left to right through what looks like an open, grassy field. They seem casually dressed—some in T-shirts, some in what might be lightweight jackets or dark tops. The individuals in the shot are not sharply detailed, because the focus is clearly on the raindrops in the foreground. The overall effect is that their figures appear in mid-stride, with a slightly ghostly or impressionistic blur. Their faces and clothing details are indistinct, but you can tell they’re moving around in a relatively relaxed manner, as if meandering through the festival stalls.

The sky or background beyond the tents is faint, likely overcast or otherwise diffused. A tree or two can be seen in silhouettes near the top left portion of the frame. Overall, the photo’s tonal range is dominated by grayscale shades and muted contrasts, suggesting either a naturally soft light or a somewhat gray, rainy day. The raindrops in focus on the glass provide the strongest contrast, appearing significantly darker or lighter against the hazy, out-of-focus scene beyond.

In summary, the photograph conveys a rainy festival or fair atmosphere, captured in black and white, with water droplets on the glass in the foreground taking precedence. The people and tents in the background are recognizable as festival-goers and stalls but are depicted in a softer, dreamlike blur that underscores both the photographer’s focus on the rainfall and the casual, everyday nature of the scene.

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

This content is only available to subscribers

Subscribe now and have access to all our stories, enjoy exclusive content and stay up to date with constant updates.

Unlock content

Follow along today, for free

Become a member and get full access to my monthly newsletter 'Dialogue' about photography, walking and exploration, and my weekly newsletter 'Closer' about the role of AI in photography. For photographers, writers, artists, and explorers alike.

Oops! There was an error sending the email, please try again.

Awesome! Now check your inbox and click the link to confirm your subscription.