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
- Alibaba Opensources ClinFusion: A Medical Multimodal Foundation Model — aigclink · 2026-08-01
- MiniMax 3 passes Turing test for AI video: writes 'Hi' on chalkboard, now open source — Kyrannio · 2026-08-01
- Testing Doubao vs. Jimeng: $30 Gets You Only 3-6 AI Video Generations — oran_ge · 2026-08-01
- Experiment Shows Training AI Image Models at 512 Resolution + Upscaling Saves VRAM — More_Bid_2197 · 2026-08-01
- 8-Hour Debug of ComfyUI Black Images Uncovers PyTorch FP16 Overflow Bug — rtsitola · 2026-08-01
- MoGe-3 by Microsoft Sets SOTA on 9 Benchmarks for High-Fidelity 3D Geometry from a Single Image — RexDouglass · 2026-08-01