Ultra-realistic Seoul street video made with Seedance 2.5, full prompt shared
SimplyAnnisa · x · 2026-09-09
User @kingofdairyque shared an ultra-realistic 30-second, 1080p, 16:9 home-video-style clip of a Seoul street fruit stall made with Seedance 2.5, along with the full prompt.
Key points:
- Uses an uploaded reference image to lock the woman's facial identity, with consistent outfit and accessories throughout.
- The prompt describes characters, stall, lighting and atmosphere item by item, demonstrating a structured long-prompt approach for AI video realism and consistency.
Related event: Seedance 2.5 Nails 2000s Home Video Realism, Prompt Shared(10 posts)→
More from Multimodal
- HeyGen side-by-side: two AI avatars of one person, one still uncanny — HeyGen · 2026-09-09
- A 2M-Param L2 Pix2Pix Model Running Real-Time on a 2012 Ivy Bridge CPU — NoenD_i0 · 2026-09-09
- Weaviate shows how to turn a messy creative archive into semantic search without renaming files — philipvollet · 2026-09-09
- Stanford's BulletTime: decoupling frame index from world time in video generation — GordonWetzstein · 2026-09-09
- MiniMax video model's text rendering is hit or miss — users hunt for a reliable fix — bluetimejt · 2026-09-09
- DIY full audiobook with local TTS: Higgs Audio beats VibeVoice, OmniVoice and Piper — HoodWinked69 · 2026-09-09