OpenAI has transitioned its text-to-image generation capabilities from DALL-E to the more advanced GPT-4o model within ChatGPT. The change streamlines the process of generating images directly while chatting. Initially reserved for paid subscribers, the GPT-4o model accessibility was briefly delayed for free users but later rolled out. However, free users must use a specific prompt format to access GPT-4o; otherwise, they will default to a lower-quality image generator. The article reflects on the initial skepticism but concludes with a more favorable view of GPT-4o's capabilities.
When OpenAI released its latest and greatest GPT-4o image generation model, I was skeptical. After testing it, I have changed my mind entirely.
With the release of GPT-4o image generation, OpenAI kept this convenient format, switching the default image generator from DALL-E to GPT-4o for paid subscribers.
If you are unimpressed when you try it in the free version, it is because the only method that activates the use of GPT-4o is typing in the shortcut '/create image'.
OpenAI does not explicitly state limits, but after generating three images from my free account, I hit my daily limit.
Collection
[
|
...
]