AI-Generated Japan Travel Video Shows Impressive Character Consistency
eyishazyer · x · 2026-09-02
A user shared a 30-second photorealistic cinematic travel-fashion music video created with Seedance 2.5. The prompt emphasized character consistency, featuring the same young woman throughout while preserving her exact identity, facial structure, long straight black hair, makeup, earrings, proportions, manicure, and white wired earbuds. The result was praised as feeling "incredibly real" for Japan.
Related event: Seedance 2.5 Tested: Prompt-Replicable Photorealistic Japan Travel Film(5 posts)→
More from Multimodal
- Blogger turns blog logo into Pixar x Grok Bot animation with Fable 5.1 — iannuttall · 2026-09-02
- 4 Favorite Midjourney V6/V7 Style sref Codes, Ready to Copy — michaelrabone · 2026-09-02
- Walt and Jessie music video with h3 vsafastvideo: 8 steps, 1.4mp, 1 hour on a 4090 — AndrewJumpen · 2026-09-02
- Fable 5.1 vs Kimi K3: cinematic quality against double the speed at half the price — iamfakhrealam · 2026-09-02
- WorldGen hands-on: one scene image becomes movable 3D assets — JaynitMakwana · 2026-09-02
- Stress-testing Midjourney SREF codes: only the styles that survive get published — tisch_eins · 2026-09-02