Doubao Video Generation Large Model Seedance 2.5 to be released in early July: supports 30-second long videos and 50 full-modal material inputs

robot
Abstract generation in progress
Golden Finance reports that on June 23, Doubao’s new video generation model, Seedance 2.5, is currently in the final stages of closed testing and is scheduled for official release in early July. It is understood that this new model mainly achieves three major core technology upgrades: Breakthrough in generation duration: the maximum duration for generating a single-segment video can reach up to 30 seconds, with significantly improved shot continuity; Extreme multimodal input: the “multi-reference capability” has been greatly upgraded, supporting up to 50 fully multimodal material items for combined input (claimed to be the most in the world), allowing users to input a large number of image assets at once for arrangement; Enhanced editing control: it features more flexible and controllable video editing and generation capabilities, aiming to further improve creators’ efficiency and the quality of finished products. (Hard AI)
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments