"Following the release of GPT-5.2 last week, OpenAI has begun rolling out a new image generation model. The company says the updated ChatGPT Images is four times faster than its predecessor. If you're a frequent ChatGPT user, you'll know it can sometimes take a while for OpenAI's servers to create images, particularly during peak times and if you're not paying for ChatGPT Plus. In that respect, any improvement in speed is welcome."
"The new version is also better at following instructions, including when you want to edit something the new model just generated. You can ask the system to add, subtract, combine, blend and even transpose elements. At the same time, OpenAI says the update offers better text rendering. That's something many image models have traditionally struggled with, but according to the company, the new ChatGPT Images is capable of handling denser and smaller text."
OpenAI is rolling out an updated ChatGPT Images model that delivers roughly four times the speed of its predecessor and improved instruction-following for edits. The model enables users to add, subtract, combine, blend and transpose elements when modifying generated images. Text rendering has been enhanced to handle denser and smaller text that many image models struggle with. A new Images section in the ChatGPT sidebar offers preset filters and prompt suggestions for user inspiration. The update arrives amid heightened competition from Google's Nano Banana Pro and contributes to ChatGPT's large user base and ongoing improvements.
Read at Engadget
Unable to calculate read time
Collection
[
|
...
]