Video prompts

[Attach your first frame image, and the last frame image if your tool supports it, then use this prompt:]

Animate from the first image to the last image.

What changes between them: [THE ONE TRANSFORMATION, e.g. "the closed box opens and the product rises out of it" / "the empty street fills with morning light" / "the character turns fro

Generate a sequence of shots featuring the same character.

**Step 1: write the character lock.** This exact text goes into every shot prompt, word for word, before anything else. Never paraphrase it.

CHARACTER LOCK:
"[NAME], a [AGE] year old [DESCRIPTION: build, height impression], with [HAIR: exact length, color, texture, and how it is

Write and shot-list an explainer video.

What we are explaining: [PRODUCT, FEATURE, OR CONCEPT]
Who is watching and what they already know: [AUDIENCE + BASELINE]
The one thing they should understand afterward: [THE SINGLE TAKEAWAY]
What they should do next: [THE ACTION]
Length: [60 / 90 / 120 seconds]
Visual style: [SCREEN RECORDING / MOT

A repeatable pipeline for a faceless channel. Run each step, check the output, then paste it into the next.

**Step 1: The script.**

```
Write a [60 / 90 / 180] second script about [TOPIC] for a [NICHE] channel.

Audience: [WHO WATCHES AND WHY]
Channel voice: [e.g. "calm and factual" / "fast and irreverent"]
Format: [top-list / single st

Write five opening hooks for a video ad, each as a generation-ready prompt.

Product: [WHAT IT IS AND WHAT IT DOES]
Audience and the moment they see this: [WHO, AND WHERE THEY ARE SCROLLING]
The problem in their words: [HOW THEY DESCRIBE IT]
What the rest of the ad shows: [SO EACH HOOK LEADS SOMEWHERE REAL]
Platform and format: [TIKTOK / 

Create a food video for [DISH OR PRODUCT].

Format: [OVERHEAD RECIPE / RESTAURANT HERO SHOT / PRODUCT REVEAL / ASMR CLOSE-UP]
Length: [SECONDS]
Mood: [warm homemade kitchen / clean modern studio / rustic outdoor / moody fine dining]

Style spine, identical across every shot:
"[LIGHTING: soft diffused daylight from a window at camera left,

[SHOT TYPE: slow dolly-in / handheld tracking shot / static wide shot] of [SUBJECT + ACTION: a lighthouse keeper climbing a spiral staircase, lantern in hand].

Setting: [LOCATION + TIME: inside a stone lighthouse at dusk, warm lantern light against cold blue dusk light through slit windows].

Camera: [MOVEMENT + LENS: dolly rises with hi

A 15-second product ad for [PRODUCT], shot like a premium DTC commercial.

Style spine (keep identical across every beat): [PALETTE + MOOD: warm neutrals with one bold accent color, soft daylight, minimal Scandinavian interior], 35mm look, soft window light with warm lamp fill, crisp focus on the product at all times.

Beat 1 (0-4s), Hook

A casual selfie-style video, handheld phone camera feel, slight natural shake. 9:16 vertical.

The speaker: a [AGE-RANGE, VIBE: "woman in her early 30s, gym clothes, hair up, zero-makeup authenticity" / "bearded guy in his 40s, ballcap, sitting in his truck"], holding the camera at arm's length, making eye contact with the lens.

Setting:

Extreme macro close-up, 9:16 vertical. Studio lighting on a dark, clean surface.

A [MATERIAL + OBJECT, the impossible-material swap is the format: "kiwi made of pale green glass" / "cube of iridescent kinetic sand" / "loaf of bread made of soft clay"], hyperreal surface detail: [TEXTURE SPECIFICS: "light refracting through the glass fles

CHARACTER BLOCK (keep word-for-word identical in every episode):
[CHARACTER: species/type + look + outfit, e.g. "A friendly sasquatch with shaggy cedar-brown fur, an olive-green hiking vest, and kind amber eyes"], who speaks in a [VOICE: "warm, low, folksy voice with unhurried delivery"], personality: [e.g. "endlessly optimistic, easily a

[Attach your image, then direct ONLY the motion, never re-describe what's in the image:]

Camera: [ONE MOVE: "slow push-in toward the subject" / "gentle handheld drift, as if someone is holding the shot" / "smooth lateral track left to right" / "slow pull-back revealing the wider scene"], [PACE: subtle and slow / deliberate].

Subject mot

Build the video for a song in three locked blocks + a shot list. Video models have no memory between clips: consistency comes entirely from repeating these blocks verbatim.

CHARACTER BIBLE (write once, paste word-for-word into EVERY shot prompt: any paraphrase causes drift):
[40-60 WORDS, EXHAUSTIVE: "A woman in her late 20s with waist-l

Build a trailer for an ORIGINAL film concept as 5 separate generations, cut together in editing. (Original characters and worlds only: trailers imitating real franchises or real actors get channels struck.)

THE FILM: [TITLE + LOGLINE + GENRE, e.g. "'SALT LINE': a lighthouse keeper discovers the tide has stopped obeying the moon. Slow-bur

Handheld medium two-shot on a busy [CITY SIDEWALK / campus quad / farmers market], [TIME: golden hour / overcast noon]. Vertical 9:16.

The interviewer: [BRIEF: "a woman in her 20s in a puffer jacket"] holds a plain handheld microphone toward the subject, only partly in frame; the subject is the star.

The subject: [THE CHARACTER, specifi

First-person POV video, 9:16 vertical; the camera IS the viewer's eyes. Slight natural head-motion sway, hands occasionally visible at the bottom of frame [doing an era-appropriate action: "pulling on rough woolen gloves" / "raising a clay cup"].

THE ERA CARD (research this before prompting: accuracy is the format's currency):
Time + pla

Generate a b-roll pack that cuts together like one shoot. The discipline: ONE master look block, repeated verbatim in every clip; only the subject line changes.

What the b-roll supports: [THE A-ROLL/PROJECT: "a talking-head video about remote work" / "my SaaS launch video" / "a coffee brand's social content"]
The cutaway moments I need t

An anime scene: [THE MOMENT: "a girl waits at a rural train crossing as the evening train thunders past" / "two rivals face off on a school rooftop, wind lifting their jackets"].

The 2D lock (without these, models render smooth 3D motion wearing an anime costume):
Hand-drawn 2D cel animation, flat cel shading with hard shadow edges, bold

Create a property walkthrough, one room per clip, built from my actual listing photos.

[THE WORKFLOW: attach the room's listing photo to each generation, starting from the real photo keeps the real architecture; text-only generation invents rooms that don't exist, which for a real listing is a problem.]

PER-ROOM PROMPT (attach that room

A talking-product ad, 8 seconds, one joke.

[STRONGLY RECOMMENDED: attach a real product photo as the reference/first frame, generated labels misspell your own brand; an inherited label stays intact.]

The product: [WHAT + WHERE IT SITS: "a hot sauce bottle on a taco truck counter" / "a tub of protein powder in a gym locker"].

Face place