[OpenAI Releases Images 2.6: From Photo to GIF, 50% Faster Image Generation] Beating AI News: OpenAI has released Images 2.6, an image generation model, finally enabling ChatGPT to directly generate GIFs. Simply enter a description or upload a photo to animate the image. Users can also adjust the animation speed, modify frame by frame, and even turn simple hand-drawn sketches into animated cartoon characters. These operations were previously impossible to perform in one step within ChatGPT. Besides animate images, the new version also solves a common problem in the image generation process: repeated modifications can easily distort people, products, and even brand logos beyond recognition. Images 2.6 enhances the consistency of multi-round editing while increasing image generation speed by 50%. Developers can use two new models via API. Flare prioritizes speed, generating images in as little as 6 seconds at low quality; Sunburst focuses more on image quality and detail, suitable for complex designs requiring repeated modifications. In addition, the API now supports circling areas to be modified on images, exporting SVG vector graphics, and adjusting the model's engagement level for complex scenes. This update is available to ChatGPT and Codex subscribers worldwide across all subscription tiers, and both models are now available via the API. OpenAI reports that users globally now generate approximately 4 billion images per week through ChatGPT, Codex, and the API. This represents an increase of approximately 1 billion images in just two months, compared to 3 billion in September of this year. [Original Link]