From Photo to Post: Generate High-Quality Copy with a Language Model in 2 Minutes
Visited an event or experienced something noteworthy and captured it in a photo? Upload the image to ChatGPT (or another LLM) and let the model generate a LinkedIn post, email, or summary based on the visual context.
We have all been there: you have attended an event, experienced something unique, or want to share a specific moment with your network. You have the photo, but now you need the text what do you write on LinkedIn or in an email?
It does not have to be complicated. Simply upload that photo to ChatGPT (or another language model) and ask the model to write a text based on the image. Within seconds, you will have a well-written, context-aware post.
Why This Works So Well
Modern language models can do more than just read text; they can analyze images. A model recognizes what is happening in a photo: people, faces, logos, slides, locations, atmosphere everything that provides context. This makes a world of difference, as a single photo often contains more information than you could easily summarize in words.
For instance, the model can identify:
- what is displayed on a presentation slide;
- that you are speaking on a stage or engaged in a conversation;
- whether it was a busy, well-attended event.
These details are used to refine the tone, content, and angle of the text. As a result, the output feels more natural, personal, and significantly richer.
How to Do It
- Select a clear photo of the moment you want to share.
- Upload the image into ChatGPT.
- Give a simple prompt, for example:
“Write a LinkedIn post of maximum 100 words based on this photo. Keep it personal and enthusiastic.”
- Review the suggestions and tweak them slightly if necessary.
In less than a minute, you have a text that perfectly matches what you want to convey.
A Few Prompt Examples
- “Create a short LinkedIn post based on this photo. Describe what is happening and why this moment was important to me.”
- “Write a professional email to clients based on this image. Briefly explain what we did during this event and invite the reader to get in touch.”
Smart Extra Tip
Use the model to generate multiple variations. For instance, ask for a formal and an informal version, or a concise version versus a longer one. This allows you to quickly choose what best fits your audience.
The Result
With one photo and a short prompt, you don’t just save time; you get better copy. The photo provides the context, the model handles the rest and you gain more time for what truly matters.
So, next time you capture a great moment: upload the photo, provide a clear instruction, and let the language model handle the writing. You will be surprised at how effective it is.
// About the author
Job van den Berg
Mede-oprichter, AI Keynote Spreker & Techondernemer
Tech-ondernemer (1989) met een achtergrond als socioloog (Research Master (MSc) in statistiek en sociologie) en een van de meest gevraagde keynote sprekers over AI en data in Nederland. Als mede-oprichter van Ai.nl, The Automation Group en Proxies leidt hij engineers die agentic AI van prototype naar productie brengen binnen enterprises. Op het podium vertaalt Job die hands-on praktijk naar concrete strategieën. Eerder was Job Chief Data bij o.a. DPG Media en Kantar. Hij is co-auteur van 5 boeken over AI waaronder 'AI Agents' en 'Handboek AI Strategie' en een veelgevraagd expert in de landelijke media.
LinkedIn
