OpenAI enables conversion of static images to animations in ChatGPT - Sarmad

OpenAI has added a new feature to its image generation tools in ChatGPT, enabling the conversion of static images and graphics into animated GIFs, while boosting image generation speed by 50 percent compared to the previous version.

The tech website The Verge reported day before yesterday that the new update to the image generation system, Images 2.6, is available for ChatGPT, the Codex platform, and the application programming interface (API). It provides capabilities to transform simple graphics, characters, logos, and product images into short, loopable animations, allowing marketers, e-commerce sellers, and content creators to produce interactive visual materials.

The feature enables the creation of expressive images and animated memes, and converts initial sketches into characters that can be used in videos and games. It also maintains consistency in character features, products, and brand visual elements during repeated edits—a challenge that has long plagued AI image generation tools.

The update also introduced two new models for developers: GPT-Image-2.6 Flare, designed to accelerate the creation process by generating an image in six seconds when low-quality settings are selected, and GPT-Image-2.6 Sunburst, which focuses on enhancing details, image clarity, and preserving the consistency of visual elements.

Additionally, the company added tools that allow users to select and edit specific parts of images, support exporting images in SVG format, and adjust settings to control complexity and layout before image generation.

The update comes amid growing adoption of AI image generation tools. OpenAI reported that users of its platforms generate approximately four billion images per week, signaling increasing reliance on these tools for visual content production.