Seedance 2.5 Hits Lumina AI: Generates 30-Second Native Videos
HeyNayeem · x · 2026-08-05
Seedance 2.5 has recently gone live on the Lumina AI platform, showcasing impressive capabilities based on hands-on testing:
- Native Long Videos: Supports generating up to 30-second videos in a single pass.
- Multimodal Inputs: Accepts up to 50 multimodal reference inputs.
- Finer Control: Offers much finer video editing control and native support for 10+ languages.
- 3D Director's Desk (Exclusive): Users can upload an image to generate a white model and connect it directly to the 2.5 reference workflow without needing third-party software.
More from Multimodal
- AI-Generated Neo-Noir Short Film 'DEAD END STORIES: LOLA' Released — Ok-Chard206 · 2026-08-05
- Generating 10-Minute AI 'Seinfeld' Episode Using Minimax h3 and GLM 5.2 — nathandreamfast · 2026-08-05
- MiniMax Video Model Demo: Generating Tom Holland Eating Street Food from 4 Images — CurieuxExplorer · 2026-08-05
- MiniMax H3 Early Access Live: Native Multimodal Generation & Precise Editing — HeyAmit_ · 2026-08-05
- Peking University Open-Sources MiniWorld for Training Video World Models on a Single 8-GPU Server — PekingUniversity · 2026-08-05
- SandAI Releases MAGI-2 Preview: 114B Audio-Video Generation Model — Nice_Amphibian_8367 · 2026-08-05