ChatGPT gains native GIF generation from OpenAI's unannounced Images 2.6 model

OpenAI is rolling out native GIF generation inside ChatGPT, letting users create animations from text prompts or uploaded photos using the unannounced Images 2.6 model. Generated GIFs can have their playback speed adjusted, be inspected frame by frame, edited, and shared. The Verge reported that OpenAI is bringing the model to ChatGPT and Codex users across web, desktop, and mobile, and that developers will receive two new API models, GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst, for faster generation and higher-quality results respectively. The rollout is gradual, and most users cannot access the feature yet; Decrypt said it could not generate GIFs on its accounts at the time of testing. OpenAI has not published a standalone announcement detailing the new model's capabilities and has not provided a specific date for full availability. The feature follows the September release of Images 2.5, which offered generation speeds up to 50 percent faster than its predecessor, and arrives months after OpenAI shut down its standalone Sora video app in March.