Finn

lazymaxxing with ai and posting the receipts

[Finn @finnardley]

@jaimintf this is beyond impressive, gj man

[Finn @finnardley]

@ChadAppDev imma do dihmaxx

[Finn @finnardley]

@andilosing if this happens to me i could very well lose my mind

[Finn @finnardley]

@aakash_env goat

[Finn @finnardley]

@petersapps lmfaooo

[Finn @finnardley]

@PranavOriginals helloo

[Finn @finnardley]

@aGim_asf @bartdarebel thanks man 🍻, any good advice when starting a new X account?

[Finn @finnardley]

opus 5.5 can recreate it actually

pure code, 0 after effects

steal the prompt ↓

<inputs>
Ask me for: the brand name (mine is "Opus 5.5"), about 25 studio photos of one model in black on white, a photo of a desk with a monitor by big windows, a cloud photo, a photo of someone working on a laptop, and a 30 second track.
</inputs>

<direction>
A 30 second AI-product launch film, 1920x1080. Paper background #e6e7e5, ink #111, one font (Inter 400, 76px, -5% tracking), a big Times New Roman wordmark in sky blue #56c6f7. Two looks carry it: a heat-map (yellow → peach → hot pink → violet, cycling) and flat paper with small black tracking squares (24px) flickering at the corners of whatever is on screen. Motion is half smooth glides, half stop-motion steps on a 25fps clock.
Banned: crossfades between scenes, drop shadows on text, bouncy easing, any color you didn't pick from the palette above.
</direction>

<structure>
29.5 seconds, 9 scenes, hard cuts only where marked.
Heat-map silhouette of a woman in profile, "Imagine to have all your tool" wipes in pink and turns white, scanlines, glitch bands (0-2.6s) → 40px pixel blocks eat the frame from the top-left with hot yellow and pink edge pixels (2.6-3.4) → "{ in }" grows to "{ in one }" to "{ in one place }", braces sliding apart, then "{ intro [3 tiny photos] ducing }" in maroon with two pale arrows drifting outwards (3-6) → a stone desk appears in heat-map on paper, the whole room follows, then turns real from the desk outwards, windows last (6.4-8.6) → CUT closer, slow push on the monitor showing the wordmark over clouds (8.6-10) → CUT into the screen: dithered clouds, wordmark, a frosted glass prompt bar (10) → 11x zoom onto the bar while "Create a neo goth model for a clothing brand." is typed, camera riding the caret (10.7-12.5) → zoom out, pointer clicks send, the arrow turns left and sweeps the text away (12.8-14.3) → CUT to paper: "Building Image" arrives in pastel and inks itself, shrinks to the top-left, four steps drop in (Processing, Generating, Image, Assemble), each pushing the list up (14.3-16.8) → colored dots fill a 17x23 grid, take the portrait's tones, turn to mosaic, then the photo (16.8-17.7) → the photo shrinks and swaps stop-motion through the set, tilts into a 3D deck, fans into a row, then one hero card with a trail receding left: "gets / better", then "you [cards] create" (17.7-24.4) → everything blurs and tints while orange, red and magenta blobs rise (24.4-25) → "The AI powered platform for modern creatives" lands word by word, white, 56px (25-28) → the words vanish, a thin strip of photo opens in perspective and settles into a white result card with the prompt text and a footer bar (28-29.5).
</structure>

<build>
1. One HTML canvas, 1920x1080. Every frame is computed from time inside seek(t): no CSS transitions, no timers.
2. Heat-map: a 1024-step cyclic palette indexed by brightness plus a phase that moves with time, drawn at half resolution and scaled up.
3. Pixel dissolve: a 48x27 grid, each block gets a value from its position plus low noise, and a threshold sweeps across it.
4. Clouds: take the cloud photo's whiteness and brightness, then a 4x4 ordered dither between sky blue and white.
5. Glass bar: a pre-blurred copy of the backdrop clipped to a rounded rect, a pale tint, a white rim. Draw the clouds with smoothing off when zoomed so the dither stays crisp.
6. 3D cards: project four corners (rotate around Y, perspective 1500px), then draw the photo as 72 vertical strips between them.
7. Gradient: five soft blobs drawn on a 192x108 canvas and scaled up, which blurs them for free. Render with Playwright, 8 subframes per frame, 60fps.
</build>

<gotchas>
The typing close-up is not a pure zoom: the bar gets slimmer as you push in. Text that grows word by word must re-center every frame or it drifts. The tracking squares and photo swaps snap to 25fps even though the film is 60. Blur the outgoing scene on a small copy, tint it by position not brightness, or you get glowing outlines.
</gotchas>

<start>
Ask me for the inputs, then show me stills of all 9 scenes before you render.
</start>

[Rajz @rajzmotion]

Let me know when Opus 5.5 can do this

[Finn @finnardley]

@aGim_asf @bartdarebel i think its pretty good in some aspects and might evolve honestly, ive had a comedy channel where i reached 150M views purely off of ai written comedic scripts

[Finn @finnardley]

@aGim_asf @bartdarebel yeah i agree, an expert motionn designer with good taste would get insane original creations out of opus

[Finn @finnardley]

@bartdarebel thanks man 🥂

[Finn @finnardley]

your launch video doesnt need a motion designer anymore

this one is pure code, opus 5.5 made it in 15 minutes

steal my prompt and swap in your brand ↓

<inputs>
Ask me for: my brand name, one photo of my product on a screen, one moody photo of a room where someone is working, 10 photos of people, my closing line (6 words), and a 20 second track.
</inputs>

<direction>
A 20.1 second brand film, laid out at 1280x720 and rendered at 1920x1080. Only black #000, white #fff, arrow blue #8fc0ff and one gold #f0aa3c. Inter 400 at -4% tracking, titles Inter 600. Text is typed, never faded: each new word lands blue and turns white in 0.2s. Half the film glides on cubic-bezier(.45,0,.15,1), half snaps on a 30fps clock. Photos are raw, slightly tilted, square corners. Everything is centered on (640,360) unless a position is given.
Banned: text gradients, drop shadows, bouncy easing, crossfades between scenes, any other color.
</direction>

<structure>
12 scenes, hard cuts at 1.6, 2.47, 3.23, 3.9, 4.8, 6.03, 7.5, 8.9, 10.1, 11.1, 13.33 seconds.
Black: a blue arrow, then "Somewhere right now" at 54px in a 1px outlined box, words at 0.5 / 0.7 / 0.93s, the newest word gold on a teal block, faint 8px mono code lines blinking around it → 1.6: the arrow turns up and grows 5x inside a soft blue ring (1.7-1.87) → 1.9-2.4: blue halftone dots on a 13px grid rise from the bottom → 2.47: the product screen full frame, blur 9px to 0 in 0.3s, slow 10% push → 3.23: the room full frame, tinted blue; an orange 3px route draws along the floor from the left edge to a blue ellipse marker (80x31) at (661,611); a white pill 426x76, radius 13, pops in at (420,321) and types "Someone is" at 37px → 3.9: close-up, room 2x and blurred, pill 130px tall at y 295, text 64px, "Someone is building with" typed while the pill slides left with the caret → 4.8: only "[brand]" in a 356x133 pill, radius 66, 6px pale blue border, text 65px; at 5.37 an 800x430 stadium lens swells around it, 1.17x → 5.8: white, the room survives inside a 924x519 stadium that shrinks to 570x285 → 6.07: a 9x9 grid of 26px grey squares (42px pitch) builds row by row around one 25px black square; at 6.73 four words in 64px caps appear near the frame edges, then lock into a staircase left of and below the square: AND at (386,243), NOBODY at (384,307), CAN at (664,440), TELL one step right at y 497 (slide 6.87-7.0, last word drops 7.03-7.17) → 7.5: a column of 288px-wide photos, 15px apart, steps up one photo every 0.15s; "The" 7.83, "ones" 8.17 at x 131, "who" 8.3, "won" 8.57 at x 915, 50px, baseline 375 → 8.9: black, "who won" in a wide soft blue ring, then "didn't" 9.27, "just" 9.4, "build" 9.6 at 51px, the line drifting left from x 590 to 270 → 10.1: white, six photos slam down at 10.1 / 10.37 / 10.57 / 10.7 / 10.83 / 10.97, the first 607 wide and the last filling the frame, tilted between -4 and +11 degrees, 7% pop → 11.1, 11.63, 12.17, 12.7: four full-screen portraits with THEY / MADE / THE / WORLD at 131px, 124px line spacing, scrolling up one line per photo so the active word sits near center, active line 97% white, others 42% → 13.33: black, "Believe." typed at 45px, blue glow from below, gone by 14.77 → 15.0: the closing line at 44px, one word every 0.167s → 17.27: a white mark pops in, slides left to x 504 (18.0-18.5), the brand name arrives beside it at 73px weight 500.
</structure>

<build>
1. One HTML canvas, every frame computed from time inside seek(t): no CSS transitions, no timers. Lay out at 1280x720, scale 1.5x.
2. Typed lines: a list of word start times, the line re-centered or drifted by keyframes, each new word blended from blue to white over 0.2s.
3. Halftone: sample the product screen per 13px cell, white dots only where it is pure white, navy in shadows, blue elsewhere, revealed behind a wavy front rising from the bottom.
4. Lens: redraw the scene 1.17x larger inside a clipped stadium, plus two hairline white rims.
5. Photo cards: four corner points, the photo drawn as 48 vertical strips between them, with a 7% scale pop that decays in 3 frames.
6. Stacked title: one keyframed scroll value moves all four lines; switch the bright line on each cut.
7. Render with Playwright, 8 subframes per frame for motion blur, 60fps.
</build>

<gotchas>
The stop-motion parts must snap on the 30fps clock even though you render at 60. Typed lines must re-center or drift every frame or they jump. The route and marker sit on the floor, so the marker is an ellipse, not a circle. Leave 0.2s of pure black before the closing line.
</gotchas>

<start>
Ask me for the inputs, then show me stills of all 12 scenes before you render.
</start>

[Finn @finnardley]

@bartdarebel valid point

[Finn @finnardley]

@algozeus_ da alrdy posted an opus 5.5 version

[Finn @finnardley]

@bulletfault @rajzmotion how so?

[Finn @finnardley]

@achxvi still waiting ❤️

[Finn @finnardley]

@achxvi can u send please?

[Finn @finnardley]

@achxvi prompt

[Finn @finnardley]

@arthuryuzbashev does it require manual intervention or can it be left to run auto?