ByteDance (Seed) · Text-to-Video
Seedance 2.5
ByteDance's audio-video model generates up to 30 seconds in one shot, extendable twice, versus Seedance 2.0's shorter clips. Takes up to 50 references (30 images, 10 video, 10 audio) against 2.0's nine images and three audio/video clips. Launched 31 July 2026; no independent benchmarks published yet.
Open the source ↗Similar Video & Animation releases
- SenseNova 6.8 Code2Video
OpenSenseNova (SenseNova) · Code-driven video model · Week 45, 2026
- OpenFilm
openfilm · Coding-agent video · Week 45, 2026
- showhow
Sirio Berati (tein) · Coded explainer reels · Week 45, 2026
- AI Video Production Editor
LudwigKienle · AI film studio · Week 45, 2026
- Freefield
neuregex · Open creative studio · Week 45, 2026
- Creative Prompting with Gemini Omni in Flow
Google Flow (Google Labs) · Video Prompting Guide · Week 41, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.