Text & titles prompts for AI video

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page. From a terminal: curl -fsSL https://varg.ai/install | sh installs the vargai CLI (https://varg.ai/how-to/cli.md): vargai search and vargai install <slug> with no key, every varg model after vargai login.

3 viral prompts with results and 0 prompt skills for text & titles: kinetic typography, animated titles, title cards and word-per-beat text.

Viral text & titles prompts with results (3)

Full prompts, verbatim from their authors, each with the model it ran on and the post's own result, best first (likes plus three times saves). Credit the author when you reuse one. Examples to remake, with varg's remake prompts, are on Text & titles.

Agent map explainer: satellite to paper map in one take

<inputs>
Ask me for: my map story in one line (a place, border, island, route or line on the map with one surprising fact) and the length (30-45 s). If I have no idea, pitch me 3 with a hook line each and let me pick. Check every fact on Wikipedia before you write a word.
</inputs>

<direction>
A 1920x1080 30 fps map explainer in the Johnny Harris / RealLifeLore look, made 100% in code as one HTML canvas page. Real satellite imagery for the close-ups, a vintage paper map for everything wider, red marker drawn on top.
Satellite: Sentinel-2 cloudless 2016 tiles from EOX (CC BY 4.0, credit "Imagery: Sentinel-2 cloudless 2016 by EOX, contains modified Copernicus Sentinel data" small in the corner). Cut the land out and lay it over a drawn navy sea (#14304A centre to #0B1E31 edges) with a soft teal shallow-water halo (#2A6274).
Paper map: ocean #A9C2C4, land #ECE2CA, countries in muted pastels (#E6C1A7, #EEDAA4, #D2DEB8), coast dark brown 1.25px over 3 soft water-lining strokes (30, 19, 10px), dashed brown borders, a 10° graticule at 26% opacity, labels in Cormorant Garamond 700 letter-spaced 8-16px.
A paper texture multiplied over everything (85% on paper, 22% on satellite), 7% film grain, warm vignette. Red marker #D9291D, 7-10px, round caps, wobbling and re-drawn at 8 fps so it boils like ink. Handwriting in Permanent Marker.
Callouts are physical paper: cream tags with a colour bar and a strip of tape (Oswald 700 54px title, Special Elite 28px subtitle typed in), torn strips with a yellow highlighter swipe, tear-off calendar pages, a red rubber stamp. A live lat/long readout in Special Elite bottom left on satellite shots.
Banned: AI video or image generation, stock footage, word-by-word captions, hard cuts (one continuous camera only), any frame where nothing moves, icon packs, glossy gradients or glass UI.
</direction>

<structure>
Length: 30-45 s at about 175 wpm, one continuous camera, no hard cuts.
0 s open tight on satellite of the subject with the hook line ("From this ___, you can ___"), a red marker circle draws around it on the key word with a handwritten word beside it → name the places: a paper tag slaps onto each one on its name, its subtitle types in on the next word → the key number: a dashed red measuring line or route draws in, with a black tag that counts up to the number → the context: a Google Earth pull-out from satellite to the paper map at continent or ocean scale in about 1.3 s, the big line, border or route draws in red marker with a handwritten label, then dive straight back in → the consequence: 2 physical props (calendar pages, clocks, price tags, flags) pop in on their words and one of them flips → the local twist: torn paper strips with yellow highlighter → the story: a red stamp slams the year with a camera shake, the frame splits into two tinted sides, a tracker card (date, time, counter) and a dotted path with a moving marker that crosses the line on the right word → the ending: pull all the way back to the big map with both sides tinted, a red circle on the subject, and a paper end card whose number gets scribbled out and replaced in marker by the real punchline, held 1.5 s after the last word.
</structure>

<build>
1. Tools (all free, all local). Install what's missing and tell me what you installed:
- Python with numpy, Pillow, OpenCV and Playwright (Edge or Chromium)
- FFmpeg
- faster-whisper small.en, int8 on the CPU
- Kokoro (kokoro-onnx) with kokoro-v1.0.onnx and voices-v1.0.bin
- d3 7.9, topojson-client 3.1, world-atlas 2.0.2 land and countries at 50m and 10m, Natural Earth ne_10m_geographic_lines (date line, equator, tropics)
- Google Fonts: Permanent Marker, Special Elite, Oswald, Cormorant Garamond
- one free tense documentary music bed, plus free SFX: pen marker line, writing scribble, paper slide, page turn, tape, whoosh in and out, impact, typing, and whatever the story needs
2. Voice (Kokoro):
- Write short lines (about 10 per 30 s) and show me the script before you record.
- Kokoro am_michael at speed 1.18, one wav per line, joined, then shrink every pause over 0.28 s to 0.2 s.
- Run every place name through Kokoro's phonemizer and respell it until it's right ("Diomede" had to become "Diameed").
- Word times: faster-whisper on the final wav, cut into chunks at every pause.
3. Timing: key every camera move, pop-in, marker stroke and SFX to a word (by its nth occurrence, since "is" and "and" repeat), never to a second, so a new voice re-times the whole film.
4. Map engine:
- Web mercator in world units (256 = the globe). Camera = focus point + its screen offset + zoom Z, at 2^Z px per unit. Zooms interpolate Z linearly under a quartic in-out ease.
- Rotate the d3 projection so the story's region never touches the antimeridian cut.
- Satellite: stitch tiles at 3 zoom levels around the subject (like z9, z11, z13). Mask the land (redder than blue by 4-6 levels after a 1.5px blur, opened and closed, specks removed, holes filled), feather the mosaic edges, fade the finer mosaics in as you zoom.
- Satellite fades to paper between Z 9.3 and 7.3.
5. Marker and paper:
- Strokes resample every ~26px and wobble ±1.5px (sine plus noise re-rolled 8 times a second). Draw a dark red underlay 1.6px wider, the red core, then a pink 30% highlight offset up-left. Circles go 1.1-1.13 turns.
- Pop-ins are a spring (damping 0.48, 19 rad/s) from 55% scale with a small rotation settle. Exits shrink and fade in 0.22 s.
- Handheld drift about ±2px and 0.06°, a 16px decaying shake on the stamp.
6. Render:
- Every frame is a pure function of time. Playwright seeks it and grabs the canvas.
- 8 motion-blur subframes over half a frame, raised up to 40 when the zoom is fast.
- Look at a contact sheet of stills and full-size crops before the full render. After it, pull frames from the finished mp4 and check those, not the page.
7. Edit and sound:
- Voice 10+ dB over the music in every phrase, the bed ducking under each word.
- One SFX per event: marker on every stroke, paper slide on every tag, page turn on every flip, a whoosh on each zoom, an impact on the stamp.
- Mix to -14 LUFS, encode H.264 CRF 19 with AAC.
</build>
<gotchas>

d3 with a custom clipExtent paints land over the whole sea when a polygon reaches the pole or is read as inverted, so drop Antarctica and any ring whose d3.geoArea is over 2π. file:// pages can't fetch JSON, so wrap the topojson as JS globals. Use only the 2016 Sentinel-2 cloudless layer (later years are non-commercial) and keep its credit in frame. Fast zooms ghost at 8 blur samples, so scale the samples with zoom speed. If your renderer injects its own global function, never give yours the same name, or every frame renders black while the stills look fine.
</gotchas>
<start>

Ask me for my map story first (or pitch me 3), fact-check it, then show me the script before you make the voice.
</start>

Model walks a rail of floating copy, side-scrolling promo

Commercial film.

Maintain the initial background color throughout the sequence.

The camera smoothly tracks the character with a continuous horizontal scrolling movement, moving alongside them as they walk.

Text and connecting lines progressively appear across the screen, forming a continuous visual pathway.

As the character walks, they recognize the text and graphic elements appearing around them as physical objects that actually exist within the same space. They naturally interact with these elements as they move forward: occasionally tapping nearby text with a fingertip, looking up at words above them, glancing sideways at graphics, slightly stepping aside to avoid an element, ducking underneath one, or briefly stopping to observe something.

A continuous line, resembling a railway track or visual route, connects one text element to the next. The text from the reference image appears sequentially along this connected path, following the original order.

The text and graphic elements must not feel like flat background decorations. They should feel physically present in the same three-dimensional space as the character, with convincing spatial relationships and interaction.

Do not repeat or duplicate any text.

Keep the overall pacing fast, rhythmic, and fluid. The horizontal scrolling movement should remain continuous and uninterrupted throughout the sequence.

Faithfully reproduce all text from the reference image without garbled characters, corrupted typography, misspellings, or altered wording.

For the final transition, a large foreground object or graphic element passes very close in front of the camera, completely covering the entire frame and creating a natural foreground-blur wipe transition.

As the foreground object clears the frame, seamlessly reveal the final logo screen.

Camera movement should be smooth, dynamic, and cinematic.

Prioritize the interaction between the character and the text / graphic elements above everything else.

BGM: Up-tempo, rhythmic music with a strong beat.

Text-behind-subject type motion on an old AI clip

Rebuild an existing video (16:9 landscape) by adding typographic motion and BGM.

[Structure] 5-layer sandwich (text behind subject)
Original video -> giant filled text -> background-removed person -> outline text in the same position -> small magazine-style parts
[Text] 'PEACH' in an extra-bold condensed face (Anton), spanning the full frame width. Small parts in a monospaced font
[Motion] Mask reveal + stagger (letters rise from below one at a time). Punch-in at the moment the peach is lowered. On the smile, a white flash swaps the word to 'JUICY'
[Beat sync] Sync the song's break -> drop to the moment the peach is lowered
[Sound] Duck the BGM (lower it automatically) only while the voice is speaking
[Color] White, ink black and one accent color
[Don't] Text over the face / text left on screen the whole time / too many colors / motion unrelated to the beat

Techniques used (author's notes):
How it works (5 stacked layers): the original video; behind, a huge 'PEACH' in filled letters; the girl cut out of the video; in front, the same 'PEACH' in the same position as a white hollow outline; small magazine-like parts -> because the text sandwiches the girl, she looks like she is inside the letters.
Motion: letters rise from below one at a time; push in hard at the moment she lowers the peach; on the smile it flashes white and swaps to 'JUICY'.
Sound: line up the most satisfying 'stop -> boom' of the song with the moment she lowers the peach; lower the music only during the 'yummy' voice line.

Prompt skills (0)

More for text & titles

Effects (8)

Guides (2)

Other kinds of skills