OpenAI Adds New Image Generation Capabilities to GPT-4o
OpenAI has added new image generation capabilities that are native to GPT-4o, saying the model can now produce precise and photorealistic images.
“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,” the company said in a Tuesday (March 25) blog post.
The model’s newly improved capabilities include text rendering that is better able to blend precise symbols with imagery, multiturn generations that allow users to refine and experiment with images through natural conversation, and instruction following that enables GPT-4o to follow detailed prompts and handle as many as 20 different objects, according to the post.
GPT-4o can also learn from user-uploaded images to inform the image generation, link its knowledge of text and images to work more efficiently, and produce images with photorealism and a variety of styles, the post said.
All images generated by GPT-4o will include C2PA metadata to identify them as being artificial intelligence (AI) generated, and OpenAI will continue to block requests that violate its content policies, per the post.
OpenAI began rolling out GPT-4o image generation to Plus, Pro, Team and Free users Tuesday, and said it will soon add Enterprise and Edu users.
“Creating and customizing images is as simple as chatting using GPT-4o — just describe what you need, including any specifics like aspect ratio, exact colors using hex codes, or a transparent background,” the company said in the post.
OpenAI launched GPT-4o in May, saying that the AI model featured text, vision and audio processing improvements and would be free for all users, with paid subscribers getting up to five times the capacity limits.
“OpenAI’s ChatGPT was already the most impressive chatbot for humanlike conversations given the range of voices and its ability to understand nuance,” Antony Cousins, who was executive director of AI strategy at Cision at the time, told PYMNTS. “The speed enhancements now make this next to indistinguishable from a human conversation.”
In August, OpenAI unveiled an update that allowed developers to fine-tune GPT-4o to suit specific business needs. This feature, long sought by the tech community, opened doors for customized AI applications across various industries, PYMNTS reported.
The post OpenAI Adds New Image Generation Capabilities to GPT-4o appeared first on PYMNTS.com.