Written by 
Chinese tech company ByteDance’s research team published a paper on ArXiv on December 5th, 2024, introducing a new framework called Infinity, aimed at improving the efficiency and quality of text-to-image synthesis. In the field of image generation, creating high-resolution and realistic images has always posed significant challenges, especially in text-to-image synthesis tasks. Traditional methods largely […]
On December 18th, at the Force Conference hosted by the Volcano Engine, ByteDance officially launched the Doubao Vision Understanding Model and announced its price at 1,000 tokens for 0.003 yuan, 85% cheaper than the industry average, which means that for one yuan, it can process 284 images of 720P resolution. This signifies ByteDance replicating its […]
According to the Chinese media Jiemian, ByteDance will soon launch a video generation model called PixelDance, ahead of Sora. ByteDance has been active in the field of large models. On September 24th, the company simultaneously released two large models, PixelDance and Seaweed, for video generation, and conducted a small-scale invitation test for creators and corporate […]