Seedance 2.5 generates 30-second consistent videos with massive asset reference
thetripathi58 · x · 2026-08-24
Seedance 2.5 is now live inside Magnific, allowing users to direct actual scenes with AI. The tool supports generating up to 30-second continuous takes without stitching. It handles complex interactions, such as multiple characters laughing simultaneously, without breaking consistency. The key differentiator is a massive reference system that accepts up to 50 assets per generation (30 images, 10 videos, 10 audio tracks). Users can control camera zoom, focus, and depth of field, and retouch specific details without regenerating the whole video.
More from Multimodal
- France's first fully AI-generated talent show: no actors, no physical set — Smooth_School1283 · 2026-08-24
- A day on the Blue's Clues set, recreated with voice cloning and b15-49 weights — Foreforks · 2026-08-24
- Hands-on: Wan 3.0 generates 30-second clips with sound on Magnific — iamfakhrealam · 2026-08-24
- LichtFeld Studio Demo: 5M Gaussians on RTX 4090 — janusch_patas · 2026-08-24
- AI Comic Character Drifts Over 40 Strips — orbitalNest · 2026-08-24
- Wan 3.0 launches on Newtake with cinematic visual generation — SimplyAnnisa · 2026-08-24