Seedance 2.5 AI video generator

Seedance 2.5 is ByteDance’s video and audio generation model, designed for longer scenes, reference control and video editing. It can interpret images, video and audio together to guide how a scene looks, moves and sounds. Riverflow supports both standard and Uncensored versions, with generation up to 30 seconds, video editing and extension.

Riverflow supports generated clips from 4 to 30 seconds for Seedance 2.5, compared with 4 to 15 seconds for Seedance 2.0. Seedance 2.5 also supports larger reference sets, video editing and extension. Its resolution and aspect-ratio rules differ, so choose settings for the selected workflow.

Seedance 2.5 Uncensored is a version of Seedance 2.5 with relaxed content filtering, supported in Riverflow. It has the same input modes, duration options and credit rates as the standard version, including multi-reference generation, video editing and extension. Provider safeguards still apply, so Uncensored does not mean every request will be accepted.

Choose Seedance 2.5 in the video model picker. When Uncensored video is enabled for your team, Riverflow automatically uses the Uncensored version. Your team’s Uncensored Model Selection setting controls this; there is no separate Uncensored picker option. Video generation requires a paid plan.

Sign in to Riverflow, open the video creation tool and choose Seedance 2.5 from the model picker. Add your brief and any required references, then review the available settings and credit cost before generating.

Seedance 2.5: 80 credits for 5s, 155 credits for 10s at 720p · 16:9 · starting image · audio off. These are generation costs; reference preparation, resolution, aspect ratio, audio and video-input workflows can change the total. Riverflow shows the full quote before you generate.