Seedance 2.5 prompt breakdown: making AI video look like a 2000s DV home tape
SimplyAnnisa · x · 2026-09-07
kingofdairyque shares the full Seedance 2.5 prompt behind a hyper-realistic clip: "AI slop looks generated, realism feels remembered." The prompt asks for a 30s 1080p 16:9 ultra-realistic video styled as an early-2000s consumer DV recording of a young Korean woman in a Seoul neighborhood, with extensive continuity constraints locking hair, outfit, accessories, proportions, and even the bottled drink across the whole clip. A masterclass in anti-slop AI video prompting.
Related event: Seedance 2.5 Recreates Early-2000s DV Home Videos, Full Prompt Shared(11 posts)→
More from Multimodal
- Segmenting every corn kernel with Muse Wonder + SAM 3.1 on Meta's Model API — keerthanpg · 2026-10-26
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26
- LichtFeld Studio v0.5.4.3 ships community-built SteadySplats, POPSpa and Voxelization — janusch_patas · 2026-10-26
- One prompt to a 2-3 min narrated short: hands-on test of Antigravity video generation — AI_Andrew · 2026-10-26
- Creator makes 10,564-frame animated short entirely with Gemini toolchain — AI_Andrew · 2026-10-26
- FLUX.3 Klein step-distilled to 4-8 steps with CFG baked in — Fit-Structure-6489 · 2026-10-26