Seedance 2.5

Assess

Platforms

A generative video creation model with long-form storytelling, multimodal referencing, and editing controls.

Why it's here

Placed in Assess: 1 article(s) of evidence from 1 source(s), led by model releases, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.

Evidence (1)

7Hacker News·8/1/2026model_release
Bytedance launches Seedance 2.5 video model
ByteDance has released Seedance 2.5, a next-generation video creation model focused on longer single-pass generation, multimodal referencing, and more precise editing. The model supports up to 30-second audio-video generations, multi-round extensions, and reference inputs across images, video clips, and audio clips, with rollout available on Jimeng AI and Doubao Pro and API access coming soon.