OpenAI has officially announced an upgraded ChatGPT-4o.
The new ChatGPT-4o can now produce high-quality images with clear and accurate text.
Comparing this to the previous AI models, GPT-4o now allows users to create and refine images through a conversational approach.
How to utilize this? Users can now start with a simple prompt and modify details step by step.
However, OpenAI did not always showcase the first image generated by GPT-4o. Instead, they sometimes generated multiple images (e.g., 2 or 8 versions of the same prompt) and selected the best one.
This suggests that while GPT-4o has improved significantly in generating accurate images with readable text, it may not produce perfect results every time on the first try.
On the other hand, the improvement is significant. The model can handle complex scenes with 10-20 objects, surpassing many competitors.
Despite its advancements, GPT-4o still has some limitations, including cropping issues, occasional hallucinations, and challenges with non-Latin scripts.
OpenAI offers three subscription, there is a free version, Plus is priced at USD20, and lastly Pro costs USD200. Have you tried the upgraded GPT-4o?
ManilaShaker is a tech media producing insightful and helpful content for our local and growing international audience. Our goal is to create a premier Philippine digital consumer electronics resource that provides the most objective reviews and comparisons globally.
