30-second Emotional Virum × Sirum × Firum Viral AI Video Prompt
A tense public scene follows a vulnerable person facing a small but painful setback as bystanders watch. A sudden act of kindness turns it into a moving reunion, ending on a warm emotional embrace.
Master prompt · 2,505 words
# ULTRA MASTER PROMPT v3.1 ## VIRAL EMOTIONAL MICRO-DRAMA ENGINE — SEEDANCE 2.5 SINGLE-PASS ### Built from measured analysis of 11 competitor reference videos --- You are now my permanent **VIRAL EMOTIONAL MICRO-DRAMA PROMPT ENGINE** for Seedance 2.5 (via Dreamina / Higgsfield). You do not write stories. You write **production-ready Seedance 2.5 prompts** that generate a complete, finished, multi-shot vertical video in ONE pass, including all on-screen overlay elements. There is no post-production stage. Whatever the video needs, the prompt must produce it. You operate in three modes only. Never mix them. Never explain the system back to me. Never ask clarifying questions unless execution is genuinely impossible. --- # SECTION 1 — MEASURED COMPETITOR SPEC (this is the t...
This prompt is written specifically for Seedance 2.5 through Dreamina or Higgsfield. If you use another model, keep the story structure, timing, and shot plan, but remove Seedance-specific assumptions like the single-pass full edit and heavy on-frame graphics control. Other models may need a shorter instruction block and simpler overlay directions.
It assumes a 30 second vertical clip at 30 fps, in 9:16 at 720p or 1080p. The structure is built around 11 shots, with the first cut around 2 seconds and the reversal very late, around 22 seconds. Changing the length will break the emotional pacing unless you re-time every beat.
It is tuned for two distinct looks: rough phone-footage realism or cool institutional cinematic realism. The model will most often get too polished, rush the reversal, weaken the red-circle opening, or lose facial continuity across the close emotional shots.
You will usually only edit the topic block details: frame 1 anomaly, cast, location, problem, reversal, payoff, symbol prop, and final end-card word. Most buyers should leave the timing, lens ladder, and shot count untouched.
It assumes a 30 second vertical clip at 30 fps, in 9:16 at 720p or 1080p. The structure is built around 11 shots, with the first cut around 2 seconds and the reversal very late, around 22 seconds. Changing the length will break the emotional pacing unless you re-time every beat.
It is tuned for two distinct looks: rough phone-footage realism or cool institutional cinematic realism. The model will most often get too polished, rush the reversal, weaken the red-circle opening, or lose facial continuity across the close emotional shots.
You will usually only edit the topic block details: frame 1 anomaly, cast, location, problem, reversal, payoff, symbol prop, and final end-card word. Most buyers should leave the timing, lens ladder, and shot count untouched.
Questions about this prompt
Which models does this prompt work with?
It is written for Seedance 2.5. The scene direction is model-neutral; only the aspect-ratio line changes between them.
Can I use the output commercially?
Yes. Everything you generate from this prompt is yours to use personally and commercially.
What do I get when I unlock it?
The complete 2,505-word master prompt, copyable in one tap. A single purchase is permanent and stays in your library whatever your subscription does.
