"OpenAI describes the new system as a 'step change' for image generation models, particularly when it comes to the tool's ability to follow instructions in detail, render dense text and place and relate objects in a scene."
"For the first time, OpenAI has also built an image model with reasoning capabilities, giving the system the ability to do things like search the web and verify its outputs."
"OpenAI says it has also put in a lot of work to make Images 2.0 better at understanding and rendering non-Latin text, with 'significant gains' when it comes to the model's ability to handle Japanese, Korean, Chinese, Hindi and Bengali."
"The new model is more flexible when it comes to aspect ratios, allowing it to generate images that are as wide as 3:1 and as tall as 1:3."
OpenAI has launched ChatGPT Images 2.0, which significantly improves image generation capabilities. The new model excels in following detailed instructions, rendering dense text, and placing objects accurately. It features reasoning capabilities, allowing it to search the web and verify outputs, enhancing reliability. The model also shows significant improvements in understanding non-Latin text, making it more effective for various languages. Additionally, it offers flexibility in aspect ratios and resolutions, making it suitable for tasks like game prototyping and storyboarding.
Read at Engadget
Unable to calculate read time
Collection
[
|
...
]