ByteDance unveils Seedance 2.5 in Beijing, saying the AI video model can generate 30-second clips from up to 50 reference materials, up from 12 for Seedance 2.0 (Juro Osawa/The Information)

<p><a href="https://www.techmeme.com/260623/p12#a260623p12" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Juro Osawa / <a href="https://www.theinformation.com/">The Information</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://www.theinformation.com/briefings/bytedance-unveils-seedance-2-5-video-model">ByteDance unveils Seedance 2.5 in Beijing, saying the AI video model can generate 30-second clips from up to 50 reference materials, up from 12 for Seedance 2.0</a></b></span>&nbsp; &mdash;&nbsp; ByteDance on Tuesday unveiled Seedance 2.5, its new AI video generation model, at a conference in Beijing.</p>