gen‑ai.news
← Back
Video

ByteDance set to launch Seedance 2.5 with 3-minute AI video output

ByteDance set to launch Seedance 2.5 with 3-minute AI video output

ByteDance is gearing up to release Seedance 2.5, the latest iteration of its AI video generation model, through its Dreamina platform. The launch is expected in July, and the most prominent upgrade is support for video outputs of up to three minutes - a significant step up from the shorter clips that most generative video tools currently produce.

Most competing models in the space, including those from Runway, Kling, and others, have largely operated within windows of a few seconds to around a minute. A three-minute ceiling changes the practical calculus for creators, allowing for more complete storytelling within a single generation rather than requiring multiple clips to be stitched together in post-production.

ByteDance has been steadily building out its generative media capabilities under the Dreamina brand, which serves as the consumer-facing surface for its image and video AI tools. Seedance has been the video-focused line within that ecosystem, and version 2.5 appears to be a mid-cycle refinement rather than a full architectural overhaul - though the output length extension alone represents a meaningful functional improvement for users.

No pricing details or regional availability specifics have been confirmed ahead of the July launch. Given ByteDance's track record of rolling out Dreamina features gradually across markets, it remains to be seen how quickly the three-minute generation capability will reach users outside of its primary markets. Creators and developers keeping an eye on the generative video space will likely want to watch how Seedance 2.5 performs on quality consistency over longer durations, since maintaining coherence across several minutes of output is one of the harder technical problems in this category.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

Google Opens Genie 4 World Model to Developers via Gemini API
Video

Google Opens Genie 4 World Model to Developers via Gemini API

Google has made Genie 4 available through the Gemini API, allowing developers to build interactive 720p environments with native audio and real-time controls. The world model can generate coherent, navigable spaces from prompts, moving it from a research curiosity toward a practical tool. Access is also rolling out to Google AI Ultra subscribers through the Project Genie interface.

Could This AI-Powered Operating System Actually Speed Up Your Video Production Flows?
Video

Could This AI-Powered Operating System Actually Speed Up Your Video Production Flows?

Lemonlight, a video production company with over 50,000 brand videos in its portfolio, has launched Hero - an AI-powered operating system designed to unify the full production pipeline in one platform. The tool aims to connect pre-production, production, post-production, and generative AI under a single roof. It targets production companies, small crews, and solo creators looking to reduce workflow fragmentation.