Seedance 2.5 makes ultra-realistic DV home video in Seoul, full prompt shared
SimplyAnnisa · x · 2026-09-08
A viral post shows just how convincing AI video has become: Seedance 2.5 generated a 30-second, 1080p, 16:9 ultra-realistic early-2000s DV home video of a young Seoul woman on a summer evening — no reference image, with consistent face, hair, and outfit throughout.
The full prompt (character spec, scene details, camera language) is included and works as a reusable template. The linked OpenClips.AI gallery adds another example: a 30-second unbroken handheld follow-shot of a pool party, with the prompt broken down second by second.
Related event: Seedance 2.5 Recreates Early-2000s DV Home Videos, Full Prompt Shared(11 posts)→
More from Multimodal
- Band's local-AI music video hits 200k views: 900 generations kept 64, 3-second clips beat face drift — Hwang0500 · 2026-10-27
- Adobe Firefly video editor walkthrough: one-sentence Quick Cut turns 32s into 20s — LudovicCreator · 2026-10-26
- Hi3D V1.0 open-sourced with 2M training assets and 90% slicing success rate — kimmonismus · 2026-10-26
- Claude Can Replace Your YouTube Thumbnail Designer in 10 Minutes — thedankoe · 2026-10-26
- User trains open-source Gaussian Splash LoRA for Qwen-Image 2.1, prompted instead of plug-and-play — Spy4killer · 2026-10-26
- Multimodal AI Is Not Useless: A Practitioner Pushes Back on Growing Skepticism — thoma_gu · 2026-10-26