ByteDance's Dreamina Launches Seedance 2.5: 50 Assets & 30s Videos
JaynitMakwana · x · 2026-08-03
Dreamina, the AI creation platform by ByteDance, has officially launched the Seedance 2.5 video generation model. This update introduces two massive production upgrades:
- Multimodal Inputs: Supports up to 50 reference assets (images, videos, and audio) in a single generation, greatly enhancing creative control.
- Extended Duration: Generates continuous video outputs up to 30 seconds long, enabling deeper and more seamless storytelling.
Paired with Dreamina's native editing workflow and multilingual support, the platform is taking a serious leap toward production-grade AI video. It currently houses the complete Seedance lineup (from 2.0 Mini to 2.5) and offers creator-friendly pricing, making it a highly cost-effective official channel for testing and scaling AI video production.
Related event: ByteDance Seedance 2.5: 50 refs, 30s video, CapCut integration(33 posts)→
More from Multimodal
- Prompt template: manga-style character sheet with multi-angle views and expressions — azed_ai · 2026-10-31
- Qwen Image 2.1 2-step distill LoRA hits v1.5, enabling realtime editing on a single GPU — linoy_tsaban · 2026-10-31
- Glif demos end-to-end brand content with hundreds of castable AI models — Puzzleheaded-King584 · 2026-10-31
- Claude Opus drives Blender MCP to build 3D models straight from 3DGS — janusch_patas · 2026-10-31
- FastSDCPU Halloween release adds Fibo 2.0 Edit Turbo image editing via OpenVINO on CPU — simpleuserhere · 2026-10-31
- d1-2B decision model skims 1864 public-domain films to answer yes/no questions — vanstriendaniel · 2026-10-31