OpenAI’s upgraded image generator has gained significant attention due to its ability to create Studio Ghibli-style images and even eerie, lifelike dolls. Now, the technology is set to reach even more users as it becomes available through OpenAI API under the new model name, gpt-image-1. Major companies like Adobe and Figma have already integrated this feature, unlocking new creative possibilities for users across various platforms.
OpenAI Versatile Image Generation Model
According to OpenAI’s blog post, the gpt-image-1 model is designed to generate images across a wide range of styles while faithfully following user instructions. Its ability to interpret custom guidelines, render text accurately, and utilize world knowledge makes it a powerful tool for diverse industries. The model opens up numerous practical applications in fields such as marketing, content creation, design, and more.
Companies like Adobe are incorporating OpenAI’s image generation technology into their suite of creative tools. Adobe Firefly and Adobe Express will now allow creators to experiment with different aesthetic styles and generate images easily, making it a valuable tool for professionals, businesses, and consumers alike. This integration is designed to provide flexibility and ease of use for creative projects.
Figma Brings Image Generation to Designers
Similarly, Figma is rolling out the new capabilities within its platform. Starting today, users of Figma Design can use gpt-image-1 to generate and edit images from simple prompts. The tool allows users to adjust styles, add or remove objects, and even expand backgrounds. This powerful feature empowers designers to rapidly explore ideas and iterate visually, offering a more dynamic design experience.
In addition, OpenAI is collaborating with other platforms like Canva, GoDaddy, and Instacart to integrate the image generation API into their services. The company’s vision is to work with developers and businesses to explore further use cases for this innovative technology.
