Tag
AI news tagged Image and video, with sources.
ChatGPT doesn’t copy an image pixel by pixel; it generates it again every time. Small differences pile up each round until a realistic photo becomes a cartoon.
“Smooth Operator,” an AI-made animation of an umbrella-carrying man roaming the city to Sade’s song, went viral fast but sparked a debate over its art styles.
A Chinese creator turned Plants vs. Zombies into a 5-minute unofficial AI fan film. One post of it on X passed 2.8 million views, and GTA 6 still isn’t out.
Creator Sovey turned Trump’s state dinner for Xi Jinping into a Hangover-style AI parody. None of it is real; the post passed 10 million views on X.
Tavus says 26 of 54 people who had one-minute video calls with its Griffin model, without being told it was AI, thought they had talked to a real person.
With Gemini 3.8 Live Avatar, organizations can pick preset avatars, while custom avatars built from a reference image are available by allowlist only.
The Biological Computing Co. says a software layer derived from measurements of living nerve cells cuts a video model’s inference costs by 80%.
Alibaba’s Qwen team opened the weights of Qwen-Image 2.1, which generates and edits images, on September 20; its license permits only non-commercial use.
Google made Gemini 3.8 Live with Live Avatar, which lip-syncs across 97 languages, available in Gemini Enterprise on September 24 with US and EU endpoints.
Alibaba released Qwen3.8-Omni-Flash on September 18. It handles text, image, audio and video in a single model with a one million token context window.