Photo by Steve Johnson on Pexels

OpenAI is broadening access to its sophisticated image generation model, known as “gpt-image-1” through its API. This technology, celebrated for its capacity to produce compelling visuals inspired by Studio Ghibli and other distinct artistic approaches, is now being integrated into a variety of platforms, most notably Adobe and Figma.

OpenAI emphasizes the model’s adaptability, stating it can “create images across diverse styles, faithfully follow custom guidelines, leverage world knowledge, and accurately render text.” Adobe intends to integrate the API into its Firefly and Express applications, providing users with expanded creative possibilities for image generation. Figma has already started incorporating “gpt-image-1” into Figma Design, allowing users to create and manipulate images directly from simple prompts. Features include style adjustments, object addition/removal, and background expansion, which aim to simplify the design workflow and accelerate idea development.

In addition to Adobe and Figma, OpenAI is partnering with Canva, GoDaddy, and Instacart to investigate further applications of its image generation API. The “gpt-image-1” model is presently accessible via the Images API, with support for the Responses API to be added soon. This widespread adoption suggests a significant transformation in how images are generated and incorporated into various workflows, spanning design, marketing, and other fields.