OpenAI introduced a major new image generator, integrating it into GPT-4o, but the new generator is proving so popular that it is melting the company’s GPUs.
OpenAI announced 4o Image Generation last week, touting the generator’s accuracy and its ability to tap gain context from GPT.
GPT‑4o image generation excels at accurately rendering text, precisely following prompts, and leveraging 4o’s inherent knowledge base and chat context—including transforming uploaded images or using them as visual inspiration. These capabilities make it easier to create exactly the image you envision, helping you communicate more effectively through visuals and advancing image generation into a practical tool with precision and power.
The new image generator improves its text capabilities, as well as its ability to refine images.
Because image generation is now native to GPT‑4o, you can refine images through natural conversation. GPT‑4o can build upon images and text in chat context, ensuring consistency throughout. For example, if you’re designing a video game character, the character’s appearance remains coherent across multiple iterations as you refine and experiment.
Unfortunately, OpenAI is now limiting access, including for paid users, because the company’s GPUs are melting because of the high demand.
Altman also said the company was addressing an issue with the image generator not generating some images that it should have.
from WebProNews https://ift.tt/MdQ6lW5
No comments:
Post a Comment