ERNIE Wizshot-ME explained: Baidu's video model for podcasts
Baidu's ERNIE Wizshot Micro-Expression turns text, images and speech into expressive video, with 4,000-character inputs on Qianfan. What is known, what is not.
Tag · video
Baidu's ERNIE Wizshot Micro-Expression turns text, images and speech into expressive video, with 4,000-character inputs on Qianfan. What is known, what is not.
ByteDance's Seedance 2.5 Flash makes video up to 30 seconds at about 0.99 yuan per second in 720p, 34% below Seedance 2.5. Specs, price per clip, API date.
PAN 2 is MBZUAI's open-weight world model that turns a scene and an action into video. Specs, license, hardware, vendor benchmarks and what is still unverified.
Gemini Omni 1.2 Flash makes video with audio up to 15 seconds at about $0.07 per second in 720p, 30% below Omni 1.1. Specs, price per clip, who should switch.
Video Rebirth's HyperFlow H3 Flash shrinks MiniMax-H3 from about 31B to 13.7B parameters, makes video and audio in 4 to 8 steps, and runs on one RTX 4090.
Wizstar's Wizshot 1.0 is a reference-to-video model: up to nine input images, 720p clips of 5 to 15 seconds, 5 credits per second. Specs, claims and caveats.