Where is the continuity in generating images with API KEY?

API
2

Yes, the code is old. It has a “look at the image” function that uses a model name that is now shut off.

The solution to your problem is to use the new model gpt-images-1 on the “edits” endpoint instead of create. You can send this model input images, along with instructions to follow. An image you use could be the basic setup of the image with people to be re-created that you’ve developed.

Let’s cook with the new model…

A smiling chef in a white uniform is cooking in a kitchen while a woman stands beside him, watching and smiling. (Captioned by AI)
A smiling chef in a white uniform is cooking in a kitchen while a woman stands beside him, watching and smiling. (Captioned by AI)1536×1024 124 KB

A chef is cooking a meal in a pan while a woman stands beside him in a kitchen, watching and smiling. (Captioned by AI)
A chef is cooking a meal in a pan while a woman stands beside him in a kitchen, watching and smiling. (Captioned by AI)1536×1024 128 KB

A chef is cooking in a kitchen while a woman stands beside him watching attentively. (Captioned by AI)
A chef is cooking in a kitchen while a woman stands beside him watching attentively. (Captioned by AI)1536×1024 124 KB

Just don’t look too closely at the spices and jars on the shelf.

On the API, pay even another $0.06 per input image when you enable an input fidelity parameter to increase the reproduction copying quality further.

This model requires a new protocol for access: you must submit to ID verification along with selfie video for an individual, for verifying an organization against one person.