My friend held up a handwritten recipe card during a video call last week. “Can you read this? I can’t figure out my grandmother’s handwriting.” I took a screenshot, pasted it into ChatGPT, and typed “What does this say?” It transcribed the entire recipe in three seconds flat. She stared at me like I’d performed some kind of magic trick.
That moment captures exactly what ChatGPT can do with images — it reads, describes, analyzes, and creates them right inside your chat window. No special software. No account upgrades. No learning curve. If you’ve been curious about AI but felt overwhelmed by the options, this is where I’d tell you to start. It’s free, it’s visual, and you’ll see results immediately.
The most common question I hear is: what can ChatGPT do with images? It can generate pictures from text descriptions, edit photos you upload, extract text from screenshots and handwritten notes, and analyze what’s actually happening in a photo. We’re going to walk through each one.
What actually changed
ChatGPT can now generate images directly in your conversation. You describe what you want — “a watercolor sunset over a mountain lake” — and it creates it. No Midjourney subscription, no Discord bot, no separate app. Just type and get.
But generation isn’t the headline. Editing is. Upload any photo and say “remove the person in the background” or “make this look like a painting” or “add a dog sitting next to me.” The AI reads your image and modifies it based on your plain-language instructions.
For someone who’s never used AI before, this is the lowest-friction entry point. You don’t need to learn prompting or understand tokens. You describe what you want, like you’d describe it to a friend.
What you can do with it today
Product photos for your business
If you sell anything online — Etsy, Shopify, Amazon — product photography is expensive. A professional shoot costs $200-500 per product. With ChatGPT’s image feature, you can:
- Upload a product photo and swap the background to a lifestyle scene
- Generate multiple variations from one photo (different angles, different settings)
- Create seasonal versions without reshooting
I tested this with a simple product photo and asked ChatGPT to “place this on a clean marble surface with soft natural lighting.” The result was indistinguishable from something I’d pay a photographer for.
Extracting text from photos and screenshots
This one surprised me most.
The accuracy problem nobody’s talking about
Here’s where I need to be honest with you. ChatGPT’s image analysis is impressive, but it makes mistakes. A Stanford study found that AI vision models misidentify objects in about 15% of real-world photos. That number jumps when you’re dealing with handwritten text, low-resolution images, or anything with cultural context the model wasn’t trained on.
I learned this the hard way when I asked ChatGPT to read a handwritten note from my grandfather. It got 80% right but completely misread a critical measurement in his recipe. The cake was… not great.
So what’s the fix? Use it as a starting point, not a final answer. When I extract text from a photo now, I always double-check the output against the original. For business-critical stuff — contracts, medical documents, financial records — I still hire a human to verify.
The same goes for image generation. ChatGPT can create stunning product photos, but it occasionally adds weird details: extra fingers, misspelled text on packaging, shadows that don’t match the light source. I’ve learned to treat the first output as a rough draft.
This isn’t a dealbreaker. It’s just how the technology works right now. And honestly? Even with these quirks, it’s saved me hundreds of hours and thousands of dollars on photography and transcription. The key is knowing where it shines and where it stumbles.
What you can do with it today
Product photos for your business
If you sell anything online — Etsy, Shopify, Amazon — product photography is expensive. A professional shoot costs $200-500 per product. With ChatGPT’s image feature, you can:
- Upload a product photo and swap the background to a lifestyle scene
- Generate multiple variations from one photo (different angles, different settings)
- Create seasonal versions without reshooting
I tested this with a simple product photo and asked ChatGPT to “place this on a clean marble surface with soft natural lighting.” The result was indistinguishable from something I’d pay a photographer for.
Extracting text from photos and screenshots
This one surprised me most.