AISystem

Seedance 2.5

ByteDance Seed's audio-video generation model, which produces 30-second clips in a single pass with multi-minute extensions and timestamp-level edits.

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to August 2, 2026 (theinnermostloop.substack.com)

Seedance 2.5 is ByteDance’s audio-video generation model, announced with one-pass 30-second clips, multi-minute extensions and timestamp-level editing. The corpus records it once, alongside the 75.4-second speedrun record; an earlier Seedance appears in February, when it cloned voices from photos.

Visit resource ↗

Development timeline

Newest reporting dates first. Reporting dates may differ from event dates.

2026-08-02: A training speedrun record falls to 75.4 seconds

Knowledge graphopen in browser →

Same as

http://www.wikidata.org/entity/Q141136321

Developed by

ByteDance

Cite or correct this record

Citation formatCitation text

Seedance 2.5
Innermost Loop KB — secondary record
Reporting date: unknown
KB permalink: https://nicholsn.github.io/innermost-loop-kb/systems/seedance-2-5
Attributed sources:
- Welcome to August 2, 2026 — https://theinnermostloop.substack.com/p/welcome-to-august-2-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.