Full prompt workflow: 30-second photorealistic travel-fashion film with Seedance 2.5
SimplyAnnisa · x · 2026-09-04
The author shares the complete prompt used to generate a 30-second, 16:9 photorealistic travel-fashion film with Seedance 2.5, demonstrating identity consistency and multi-scene storytelling.
Key prompt techniques:
- Identity preservation: one woman keeps exact face, hair, makeup, earrings, body proportions and manicure throughout; explicitly bans face drift, morphing, distorted anatomy and plastic skin.
- Cinematic specs: 24fps, 180° shutter, natural motion blur, subtle film grain; only physically achievable camera moves; 24mm environmental shots, 35/50mm portraits, 85mm details.
- Three-act wardrobe: 0–7s NYC brownstones (denim), 7–16s farmers market (terracotta knit), 16–30s California coast (black bomber), outfit changes only at fixed timestamps.
- Realism constraints: correct walking mechanics, clothing physics, no duplicated people, teleportation, warped architecture, logos or watermarks.
- Audio: location sound only — traffic, footsteps, market ambience, ocean, wind, natural laughter; no dialogue or soundtrack.
- Goal: feels like a real personal vlog, not a staged commercial.
More from Multimodal
- Voxtral 3 ships a LiveKit-based voice agent SDK streaming listen-think-speak — MistralAI · 2026-10-21
- Voxtral Mini TTS 3 hits SOTA expressiveness in 35+ languages with tag-based control — MistralAI · 2026-10-21
- Mistral launches Voxtral 3 speech models and new Voice Agents API — MistralAI · 2026-10-21
- Open-sourced pixel art normals generator ships as Rust CLI and wasm library — HugoDuprez · 2026-10-20
- Fibo 2.0 is strongest for ecommerce and creator content, weakest at UIUX design — ArtificialAnlys · 2026-10-20
- Fibo 2.0 leads old Fibo on all 9 capabilities, best at reasoning and anatomy — ArtificialAnlys · 2026-10-20