ByteDance appears close to releasing Dreamina Seedance 2.5, with current rumors pointing to a possible July 9 launch. Public Dreamina and CapCut pages already reference the model, while third-party reports suggest an early-July rollout window rather than a confirmed date. Availability is expected across Dreamina, CapCut, and partner platforms that already work with ByteDance’s video stack.
Coming soon: Dreamina Seedance 2.5 is arriving on CapCut.
— CapCut (@capcutapp) July 4, 2026
Seamless generation and editing. Up to 50 multimodal references. 30-second scenes in one shot. Finer creative control. More reliable results. It's built to make creating faster, smoother, and more intuitive.
Whether… pic.twitter.com/hkJnP3zg6Y
The main new feature will be a move from short clips to 30-second standard video generation. Dreamina pages describe a long video workflow that can generate 30-second scenes, 90-second drafts, and 180-second outputs, making three-minute AI video the biggest claimed shift for this release. The open question is not only about duration but also about whether the model can keep character identity, motion, camera logic, and prompt intent stable across extensions.
You can create cinematic videos up to 30 seconds in standard mode or extend them to 180 seconds with the beta long-video mode.

For creators, advertisers, anime editors, social video accounts, and AI filmmakers, this would turn Seedance from a short-shot generator into a tool for longer sequences. The likely location is within Dreamina’s Seedance workflow, CapCut’s creator tools, and partner apps that use ByteDance’s model access. The evidence appears to come from public-facing product pages and platform copy, while the July 9 timing remains rumor-level until ByteDance posts a dated release notice.
The company behind the model is ByteDance, which has been tying AI video to its creator ecosystem through Dreamina, CapCut, TikTok-adjacent production flows, and API distribution. Seedance 2.0 is still positioned around motion stability, multimodal references, and audio-video generation, with listed durations of 4 to 15 seconds on BytePlus. Seedance 2.5 would push that strategy toward longer commercial storytelling and creator workflows, while Google’s Veo and Gemini Omni remain the clearest competitive pressure after OpenAI discontinued Sora’s web and app product on April 26, 2026.