ByteDance Launches Seedance 2.5: Generates 30s Videos, Accepts 50+ Multimodal Inputs
赛博禅心 · wechat · 2026-07-31
ByteDance's Seed team has officially released Seedance 2.5, its latest AI video generation model. The upgrade focuses on long-form storytelling and multimodal capabilities, extending single-shot high-quality video generation to 30 seconds with support for multi-round extensions.
Key upgrades include:
- Extensive Multimodal References: Accepts up to 30 images, 10 videos, and 10 audio clips simultaneously to accurately reproduce complex group scenes and multi-camera setups.
- Precise Timestamp Editing: Allows targeted modifications of characters, actions, and audio within specific timeframes, featuring advanced green screen replacement and camera movement adjustments.
- Visual & Physics Refinement: Systematically reduces the unnatural "AI gloss" and improves the realism of lighting and physical rules.
The model is now available on Jimeng AI and Doubao Pro, with API access coming to Volcano Engine soon. It can also generate synthetic data for industrial manufacturing, embodied AI, and autonomous driving training.
Related event: ByteDance Releases Seedance 2.5: Native 30s Video and Multimodal Control(60 posts)→
More from Multimodal
- BEEBS: An AI-Designed Concept Sneaker With Molded EVA Foam Upper — Delahuntagram · 2026-10-31
- AI-Generated Halloween Maid Photos Are Indistinguishable From Real Street Shots — AlchainHust · 2026-10-31
- Star Wars 'dark side' AI images with Vader shadows and a Death Star cloud — egeberkina · 2026-10-31
- MiniMax H3 generates a convincing 90s sitcom scene — Certain_Potato_4509 · 2026-10-31
- Halloween MV 'Skeleton Dogs Don't Need Walkies' stitched from six AI tools — LudovicCreator · 2026-10-31
- Ghost vs Grandma: A Halloween AI Image Meme Made with Dreamina, Prompt Included — umesh_ai · 2026-10-31