From photo to post: how to create strong texts with a language model in 2 minutes

You probably know it: you've been to an event, experienced something wonderful, or want to share a moment with your network. You have a photo of it, but now the text — what do you include on LinkedIn or in an email?

That doesn't have to be complicated at all. Simply upload that photo into ChatGPT (or another language model) and ask the model to write a text based on the image. Within seconds, you'll have a well-written, contextual post.

Why that works so well

Nowadays, a language model can not only read text but also analyse images. It recognizes what happens in a photo: people, faces, logos, slides, locations, atmosphere — anything that provides context. That makes a world of difference, because one photo often contains more information than you could summarize in words.

This is how the model can see:

• what's on a presentation slide,
• that you are speaking or talking on stage,
• or that it was a busy event.

These details are used to improve the tone, content, and angle of the text. As a result, the output feels more natural, personal and much richer.

This is how you do it

1. Choose a clear photo from the moment you want to share.
2. Upload image in ChatGPT.
3. Give a simple assignment, for example:

“Write a LinkedIn post of up to 100 words based on this photo. Keep it personal and enthusiastic.”

1. Check out the suggestions and adjust them slightly if necessary.

Within a minute, you'll have a text that fits exactly what you want to convey.

A few examples of prompts

• “Make a short LinkedIn post based on this photo. Describe what happened and why this moment was important to me.”
• “Write a business email to clients based on this image. Briefly tell us what we did at this event and invite the reader to get in touch.”

Smart extra tip

You can also use the model to create multiple variants. For example, ask for a formal and an informal version, or a short and a longer one. So you can quickly choose what suits your audience best.

The result

With one photo and a short prompt, you not only save time, but you also get better texts. The photo provides context, the model does the rest — and you have more time for what really matters.

So the next time you capture a fun moment, upload the photo, give a clear assignment, and let the language model do the writing. You'll be surprised how well that works.