ChatGPT Images 2.5 cuts generation latency by 50%, improves transparent backgrounds and multi-turn editing, with Flare and Sunburst API models.
image generation
Microsoft announced MAI-Image-1, its first in-house AI image generation model, now in testing for Copilot and Bing Image Creator, signaling a major push for technological self-reliance.
Google's new Gemini model brings major upgrades to AI image editing, focusing on character consistency, multi-stage edits, and digital watermarks for transparency.
Meta has partnered with Midjourney, gaining access to their advanced AI image and video generation tech to enhance its own creative offerings and compete with rivals.
A C++ backdoor named Pickai is actively exploiting ComfyUI servers, compromising nearly 700 AI image generation hosts and posing a supply chain risk
Google I/O 2025: Flow, Veo 3 (with audio), and Imagen 4 revealed for advanced AI-powered video and image creation.