TECH Signal 308
Seedance 2.5
The extension from 15 to 30 seconds per pass, combined with multi-round extensions, allows for the production of multi-minute, narrative-driven videos rather than isolated clips. The addition of timestamp-level editing and expanded multimodal reference inputs provides developers and creators with more granular control over the output, bridging the gap between basic generation and professional editing workflows.
Written by elseif from the cluster below · every claim links back to a sourceThe three things worth knowing
Single-pass video generation length has increased from 15 to 30 seconds, and multi-round extensions enable the creation of consistent, multi-minute content.
Users can input up to 30 images, 10 video clips, and 10 audio clips simultaneously to guide the model's output.
The model introduces timestamp-level editing for targeted audio and video adjustments, alongside advanced features like green screen and camera perspective control.
THE CLUSTER