ByteDance Launches Seedance 2.5: 30-Second Videos from 50 Reference Assets
rohanpaul_ai · x · 2026-08-03
ByteDance's Dreamina introduces Seedance 2.5, a new video generation model. Moving beyond pure text prompts, it allows users to input up to 50 reference assets simultaneously (including 30 images, 10 videos, and 10 audio clips) to maintain consistency in characters, sets, and audiovisual styles.
The model also features Timestamp Prompting, letting creators assign specific actions to defined intervals (e.g., [0s-5s], [5s-10s]) like a shot list, generating up to 30 seconds of continuous video in one take. It is exclusively available on Dreamina for the first 7 days.
Related event: ByteDance Seedance 2.5: 50 refs, 30s video, CapCut integration(33 posts)→
More from Multimodal
- 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
- PotionUI: an open-source AI media studio built by 8 parallel Claude Code subagents in git worktrees — 0roborus_ · 2026-10-31