88Z AI, 23 June — ByteDance officially released the Doubao video generation model Seedance 2.5 at the Volcano Engine FORCE conference. Currently in the final stages of beta testing, the model is scheduled for launch in early July, featuring breakthroughs in video duration, multimodal input, and controllable editing.
At a glance
- Seedance 2.5 is set to launch in early July, supporting direct 30-second native video generation and input of 50 multimodal references.
- The model features local controllable editing and can stably process nearly 100,000 white models to generate professional 3D rendered videos.
The update
At the 2026 Volcano Engine FORCE conference, ByteDance officially launched its latest Doubao video generation model, Seedance 2.5. The model is currently in the final phase of beta testing and is scheduled for public release in early July. This update achieves three global technological breakthroughs: it supports the direct native generation of 30-second video clips in a single segment; allows users to input up to 50 multimodal reference materials jointly; and features precise local controllable editing capabilities. Furthermore, Seedance 2.5 demonstrates stable performance in professional content creation, efficiently handling 3D asset production tasks. Tests indicate that even when processing nearly 100,000 white model inputs, the model generates high-quality videos with stable rendering, showcasing robust industrial-grade application potential.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- APPSOSource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.