ByteDance Launches Seedance 2.5: Native 30s Generation and Precise Editing
量子位 · wechat · 2026-07-31
ByteDance officially released its proprietary video model, Seedance 2.5, now available on Jimeng AI. The new model achieves major breakthroughs in video generation duration, controllability, and adaptation to professional workflows.
- Native 30s Output: Breaking the industry's common 5-15 second limit, it supports native generation of a single 30-second video, extendable up to 3 minutes, while maintaining extremely high character and scene consistency across long shots.
- Precise Video Editing: Adds editing capabilities like local modifications and element addition/deletion. It also supports precise timestamp commands (error controlled within 1 second), drastically reducing the cost of repeated 'gacha' rolls.
- Professional Pipeline Integration: Supports up to 50 reference materials, can directly read green screen and white model assets for generation, and can be invoked via Maya/Blender plugins, significantly boosting production efficiency for the film, advertising, and gaming industries.
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