Seedance 2.5 by ByteDance: Video AI Surpasses 30 Seconds
Le brief IA que les pros lisent chaque soir
Les 7 actus IA du jour, décryptées en 5 min. Gratuit.
Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.
Choisis ton rythme
Gratuit · Pas de spam · Désabonnement en 1 clic
Seedance 2.5 from ByteDance: Video AI Exceeds 30 Seconds
ByteDance has unveiled five new AI models at the FORCE conference hosted by Volcano Engine. The flagship model is Seedance 2.5, a video model set to launch in early July.
Volcano Engine is ByteDance's cloud division, offering the company's AI models as services for businesses. The new model generates unique video clips lasting up to 30 seconds without any post-editing, featuring scene changes and tempo variations. It can process up to 50 additional inputs simultaneously—reference images, audio, and more—which is useful for film scenes with multiple characters. Users can also edit the generated videos afterward while maintaining the original visual style and appearance.
Seedance 2.0 Gains 4K Support, and Four New Models Join the Lineup
Meanwhile, Seedance 2.0 now supports native 4K with a color depth of 10 bits. Volcano Engine also announced the Doubao 2.1 Pro language model, the Seedream 5.0 Pro image model, and the Seed-Audio 1.0 audio model. According to the company, Doubao 2.1 Pro costs about 80% less than Claude Opus 4.6.
Brief IA — L'actualité IA en français
L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.