Switch for gpt image gen in long context prompts lead to "Connection interrupted. Waiting for the complete answer"

Since the last addition of GPT 5.6 for testing, the image gen system has been having constant trouble rendering images in the chat. In my case, about 30% of the generations are never rendered in the chat, leading to the message “Connection interrupted. Waiting for the complete answer” or “Image generation failed, try again”.

Thanks for your valuable work, OpenAI team. I am bringing this to your attention because it has been happening for about four days in a row, with no interruption.

Other related bug: If the page is refreshed, it will appear: “Too many requests” leading to the permanent loss of that chat.

Another detail I found: the problem seems related only to when generating images using “5.5 instant”, not other models.

The problem is still alive. Happens more consistently when using custom GPTs.

For about two hours, " image generation failed " started to happen even for very short/simple prompts.