- AI Powered Agents
- Posts
- Any photo reimagined by AI?
Any photo reimagined by AI?
Seeing is conceiving when it comes to ChatGPT Vision
Want to re-create photos with Dall-e3?
Here’s something I tried yesterday - again with ChatGPT’s new vision capabilities.
I started with this photo of our crazy fur family - incidentally named after the Schitt’s Creek kids - Dave (David), Lexi (Alexis) and Stevie (The Rosebud Motel’s receptionist, turned owner).
![Uploaded image](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/ae43b5b6-860f-44cd-a1e4-7b2c58989be0/b54ced3c-b2df-452c-807b-0082e0f9c8fc_1536x1152.jpg?t=1710392211)
My prompt was simply:
Please provide a detailed description of what’s in this photo
ChatGPT gave me a reasonable description; here it is:
Certainly.
The photograph showcases three pets: two dogs and one cat, positioned in a home setting. The closest dog appears to be of a curly-coated breed, potentially a poodle mix, and is black or dark grey in colour. Its eyes are prominently visible, indicating curiosity or attentiveness.
Behind the first dog is a second one, with a curly and tawny coat, possibly of a breed like the Labradoodle. This dog is looking directly at the camera, offering a clear view of its light-coloured eyes and moist nose.
To the right is a cat with a striped tabby pattern in its fur. The feline displays a mix of brown and grey tones, with striking greenish-yellow eyes, gazing calmly and directly forward.
In the backdrop, a well-lit living space is visible, featuring modern interior design elements. One can see a table, a rug, and a few other furnishings. The entire scene emanates a sense of domestic comfort and serenity.
So then I simply switched ChatGPT to Dall-e mode and pasted the description as my prompt so that it would generate images based on my description.
Here they are:
![](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/d7bcf46b-8bdd-4750-87bb-cd89690b9012/8c3a7e04-6f08-4e21-aa42-0aec9b1f0073_1992x1656.jpg?t=1710392212)
As you can see, images 1 and 3 are pretty on the money - the others curiously not so much - Stevie got turned into a cat.
This one still needs work
So, I thought I was pretty clever with this because I got a good result on the first go - and maybe it works well for pets!
I tried this prompt on both a photo of me and a photo of the house and got mixed results:
![Uploaded image](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/4140158d-5c9b-447f-980a-1bb8592e106e/c15a7eb0-aeae-4bea-a777-e82277558e58_5000x3075.jpg?t=1710392213)
![](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/7b7d68c3-45a3-45b1-9d59-06e946f3d7e4/a2c0fc71-3ae8-4a3e-b506-a75f0b998e5a_1686x1816.jpg?t=1710392213)
![Uploaded image](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/5e391c5e-c7a7-4df9-b0ae-496773ec259f/5b91e1ee-02d5-4724-8940-7783b8e8b3b4_1768x768.jpg?t=1710392214)
![](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/cfa5a57c-1b04-40a6-96e9-6b593883e177/c734e8c1-eac7-40c3-8519-8833e9fb07ee_1720x1688.jpg?t=1710392215)
I can’t argue that the images do reflect the description that ChatGPT generated, but not really the original image.
So we won’t be doing Superheroes with Dall-e just yet, but you never know, maybe soon.
Happy Hunting 🚀
Reply