Lovart Integrates Seedance 2.5: Supports 50 Reference Inputs and 30s Videos

AIwithGhotai · x · 2026-08-07

AI design platform Lovart has integrated the Seedance 2.5 video generation model, focusing on multimodal references and consistency control. The new version supports up to 50 reference inputs to maintain identical characters, products, and visual styles across different shots.

Additionally, the model supports video outputs up to 30 seconds and introduces a video editing workflow, allowing users to modify, extend, reconstruct, and restyle videos. Lovart primarily targets designers, marketers, and e-commerce professionals, offering capabilities to batch-generate brand assets and product showcase videos.

Related event: Lovart Integrates Seedance 2.5 for One-Stop Video Generation(3 posts)→

Original post →

More from Multimodal

Multimodal channel →