OpenAI’s latest ChatGPT update is one of its best, bringing a massive upgrade to GPT-4o image generation. Now, instead of switching to DALL-E 3, you can generate extremely high-quality images with GPT-4o without starting a new chat.
However, there’s a catch for ChatGPT’s free users—at least, there is for now.
ChatGPT’s Image Generation Receives an Enormous Upgrade
OpenAI’s GPT-4o model is the go-to for most default conversations on ChatGPT. It works for a huge range of questions, with OpenAI labelling the model “Great for most questions.” And it is; it hits a wide range of information with speed and accuracy—but only text.
Following its March 25, 2025, update, GPT-4o can generate high-quality images with amazing detail, exceeding the quality of the model it basically replaces (DALL-E 3). Furthermore, GPT-4o can now perform editing and image adjustments far beyond the capabilities of DALL-E 3. Image editing, color and style adjustments, subtle changes, foreground and background objects, and more are all possible.
Text generation is also startlingly improved. DALLE-3’s text generation was never a strong point (though it’s not a strong point for most AI models). Now, GPT-4o can create detailed infographics with detailed explanations on nearly any topic. Text placement within images is now precise, using specific text styles and direction without the risk of creating blurry AI-slop. Detail retention is also another clear improvement, with specific features now easily transferable from one image to another without ChatGPT completely altering the scene or generating a completely new image.
Part of the upgraded image quality comes from OpenAI’s partnerships with companies like Shutterstock and a group of trainers that spent long hours specifying mistakes GPT-4o made during image generation. Talking to the Wall Street Journal, lead researcher Gabriel Goh explained that this reinforcement learning technique enables GPT-4o to accurately follow human instructions over a vast range of image generation requests but that it only required “a little more than 100 human workers” to complete the process.
ChatGPT’s new image generation really is amazing, and I’d advise anyone to try it on any topic you desire. Now, it’s not perfect; no AI image generation tool is. But it’s a remarkable jump in quality from an AI image generation model like DALL-E 3, which was useful but not amazing, to the quality GPT-4o is now capable of.
ChatGPT’s Amazing Image Update Is Rolling Out to (Nearly) Everyone
Unfortuantely, due to the unprecidented demand on GPT-4o, ChatGPT’s free users are one again forced to wait for this new feature. On March 26, 2025, OpenAI CEO Sam Altman confirmed the delay without adding a specific period for its end.
The surge in interest was expected, but not quite as much. Unfortunately, that means you’ll have to wait a little longer or upgrade to ChatGPT Plus for 20 bucks per month. In fairness, with upgrades like this, upgrading to ChatGPT Plus becomes worth the money—more so than the launch of OpenAI’s previous model upgrade, GPT-4.5.
It’s also worth noting that as part of the GPT-4o upgrade, DALL-E 3 becomes “OpenAI’s legacy image generation model.” This means OpenAI will eventually remove DALL-E 3 from ChatGPT, though there is currently no specified timeline for this change.
