zero's banner
zero's profile picture

zero

@twoclipping • 8,805 subscribers

distribution for apps + brands @affiliatenw | ugc at scale 15B+ views across our campaigns

Shorts

opus 5.5 is f*cking cracked at motion design this entire video is code, 0 after effects im open sourcing the prompt template for these motion designs steal it to recreate these ↓ Ask me for: 8 to 12 UI states I want the shape to become (e.g. button, loader, player, slider, toggle, tabs, chart, command palette, toast), pure black and white or one accent color, and a royalty-free song around 120 BPM (e.g. Mixkit, free for commercial use). Dribbble-level UI motion. One shape, never cut: every state is the same element morphing its size, radius and color while its content swaps with a short blur. A cursor drives every change with real clicks and drags. Light warm-gray canvas, black and white components, one clean UI font (Geist). Springs everywhere, a tiny overshoot at most. The camera zooms so each state fills the frame. The last frame is the first frame, so it loops. Banned: bouncy easing, particle bursts, glows, gradients on UI chrome, mismatched icon strokes, dead time, anything that looks like a template. 120 BPM, 7 bars, something happens on every beat. Button → loader → check → dynamic island → music player with a play/pause morph → scrub the progress bar → it becomes a volume slider that stretches when dragged past max → a toggle flips on the beat → the knob becomes a liquid tab indicator → the tabs open into a chart that draws itself, with a tooltip on hover → it collapses into ⌘K → type to filter → enter → toast → back to the button. 1. One HTML file, square 1440x1440. Every style is computed from time inside seek(t): no CSS transitions, no timers, no state carried between frames. 2. Springs are closed-form step responses. A value that changes target many times is the sum of one spring per change, so it stays a pure function of time. 3. The tab indicator's two edges ride different springs, so the leading edge stretches ahead of the trailing one. Same trick for the toggle knob. 4. Drags are direct manipulation: while the cursor is held, the value is computed from its position. On release it springs back from wherever it was. 5. Analyze the song with numpy for the beat grid and start on a downbeat. Place every UI sound by its measured peak. 6. Render with Playwright: 4 subframes per frame, blended with ffmpeg tmix for motion blur at 60fps. 7. Render one frame per beat before the full render. Fix anything off the grid, cramped or hard to read. Never put will-change on anything the camera scales or the text renders blurry. Text that swaps inside a morphing container needs its own enter and exit timing or it overlaps. Make the last frame identical to the first, cursor position and speed included, or the loop stutters. Ask me for the inputs, then show me the state list on the beat grid before you write any code.

opus 5.5 is f*cking cracked at motion design this entire video is code, 0 after effects im open sourcing the prompt template for these motion designs steal it to recreate these ↓ Ask me for: 8 to 12 UI states I want the shape to become (e.g. button, loader, player, slider, toggle, tabs, chart, command palette, toast), pure black and white or one accent color, and a royalty-free song around 120 BPM (e.g. Mixkit, free for commercial use). Dribbble-level UI motion. One shape, never cut: every state is the same element morphing its size, radius and color while its content swaps with a short blur. A cursor drives every change with real clicks and drags. Light warm-gray canvas, black and white components, one clean UI font (Geist). Springs everywhere, a tiny overshoot at most. The camera zooms so each state fills the frame. The last frame is the first frame, so it loops. Banned: bouncy easing, particle bursts, glows, gradients on UI chrome, mismatched icon strokes, dead time, anything that looks like a template. 120 BPM, 7 bars, something happens on every beat. Button → loader → check → dynamic island → music player with a play/pause morph → scrub the progress bar → it becomes a volume slider that stretches when dragged past max → a toggle flips on the beat → the knob becomes a liquid tab indicator → the tabs open into a chart that draws itself, with a tooltip on hover → it collapses into ⌘K → type to filter → enter → toast → back to the button. 1. One HTML file, square 1440x1440. Every style is computed from time inside seek(t): no CSS transitions, no timers, no state carried between frames. 2. Springs are closed-form step responses. A value that changes target many times is the sum of one spring per change, so it stays a pure function of time. 3. The tab indicator's two edges ride different springs, so the leading edge stretches ahead of the trailing one. Same trick for the toggle knob. 4. Drags are direct manipulation: while the cursor is held, the value is computed from its position. On release it springs back from wherever it was. 5. Analyze the song with numpy for the beat grid and start on a downbeat. Place every UI sound by its measured peak. 6. Render with Playwright: 4 subframes per frame, blended with ffmpeg tmix for motion blur at 60fps. 7. Render one frame per beat before the full render. Fix anything off the grid, cramped or hard to read. Never put will-change on anything the camera scales or the text renders blurry. Text that swaps inside a morphing container needs its own enter and exit timing or it overlaps. Make the last frame identical to the first, cursor position and speed included, or the loop stutters. Ask me for the inputs, then show me the state list on the beat grid before you write any code.

1,167,467 次观看

send your landing page to claude with this prompt ull get a video like this, made with code for free thank me later ↓ Ask me for: my landing page link, my brand name and logo mark, a two-part closing line (a statement, then a short italic tail), and a 15 second track (optional). A 14.5 second 3D fly-over of my landing page, 1440x1152 at 60fps. The page lies flat on a bright studio floor (#f9fbfb in the middle, #f2f3f6 in the corners) with a soft wide shadow around it and 24px rounded corners. One continuous camera, never a cut: it starts low over the hero and glides backwards down the page at one steady speed while looking up it, rises straight overhead to show the whole page as one strip, dives into the hero and lands it as a card under a two-line title. Focus is razor thin in front of the subject and almost none behind it, so everything near the lens melts. Cards float a little above the page with soft shadows; photos, chips and the testimonial lift off and stand up toward the lens as the camera passes them. Four small tiles of my logo lift off beside the hero button and stay with the film until the end card. The title is Geist 500, the italic tail Instrument Serif. Banned: cuts, crossfades, stops or surges in the glide, the camera turning or swinging sideways, zooming in and back out, glows, any text laid over the page before the end card. 14.5 seconds: flight 0-8.2s, rise 7.75-9.25s, overhead 9.25-9.47s, dive 9.47-9.97s, title card 9.97-14.5s. The camera 56° off straight-down and 1360px from the point it looks at, centred on the top half of the hero, the phone or product mockup sharp, four 32px logo tiles beside the button → 0-0.6: the glide eases in from rest → 0.1-1.35: the tiles lift, grow to 140-200px and hang just outside the page's top corners while the hero's chips rise to 60-80px and stand up 30° → 1.25-1.6: the glide doubles to cruising speed as the hero falls behind → 1.6: the second section's title passes the centre of the frame, its photos blurred near the lens → 1.35-2.7: that section's main photos lift to 100-130px and stand up 46°, two of its chips fly up to about 200px, stand up 54° and pass the left and right edges at 2.5 → 1.2-2.4: the tiles trail the camera 300px down the page, then drift out of the top → 3.0-7.3: every following section passes through at the same steady speed, each one sharp as it crosses the middle of the frame and soft below it; a logo tile drifts past the left edge close and blurred at 5.4 → 5.45-6.3: the testimonial card rises from 22 to 112px, stands up 30° and shows a 34px white edge → 7.3-8.2: the glide eases off as the footer arrives, the footer title sharp at 8.0 → 7.75-9.25: the rise, zooming out at an even rate while the tilt flattens (8.15-8.95) and the page's bottom edge settles 42px above the frame bottom → 9.25-9.47: the whole page as one centred strip, creeping 3.5% closer → 9.47-9.97: the dive, the page's top edge pinned to the frame top while it grows, everything below the hero fading out, then the top drops to y 283 so the hero lands as a 1018px wide card with 38px corners and a soft shadow; two logo tiles sit on its top corners, one crisp at the right edge, two huge soft blurs drift in at the bottom corners → 10.02: a white badge pill (logo + brand, 21px) fades in at y 44 → 10.12: line 1 at 74px, one word every 0.06s → 10.36: the italic tail at 82px in grey #8b8b92, one word every 0.05s, each word rising 16px out of a 12px blur in 0.34s → 10.6-14.5: hold, the card creeping 2% closer, the tiles drifting a few px. 1. Open my link in headless Chromium (Playwright) at 1440px wide, device scale 2, and scroll to the bottom once so lazy images and scroll animations finish. Mark the pieces that lift (cards, phone or product mockups, chips, feature photos, the testimonial, the hero button) with data-layer. Screenshot the full page with them hidden, then each piece alone on a transparent background with 28px padding, and save every piece's page position to a JSON. 2. One WebGL2 film page, 1440x1152, every frame computed from time inside seek(t): no timers, no CSS transitions. The page is a textured quad on the floor and each piece its own quad at its height, drawn lowest first with no depth buffer. Use mipmaps and 16x anisotropic filtering or the far text shimmers. 3. Drive the camera from one speed curve, never from a position key every half second. Focal length 1880px, 56° tilt, distance easing out from 1360 to 1700px and never back in, no turning. Speed down the page as a share of cruise (cruise is about 770 page px/s): 0 at 0s, 0.5 by 0.6s, held at 0.5 to 1.25s, 1.0 by 1.6s, held between 0.94 and 1.1 to 7.3s, then easing to 0.12 by 8.3s. Integrate it into the page position. 4. Depth of field per pixel: blur radius = 75 x (focus - depth) / depth in front of the focus and 6 x (depth - focus) / depth behind it, capped at 120px, 40 taps on a golden-angle disc, each tap read from a mip level matched to the blur. Keep the focus on whatever crosses the middle of the frame. 5. A lifted piece stands up by turning about its own middle, top edge rising toward the lens. Each casts a shadow on whatever is under it: the same picture in flat #1a2133, offset (0.10z, 4 + 0.36z), blurred 7 + 0.5z, 26% opacity. 6. Rise: zoom out in log scale with a smooth trapezoid speed (speeding up 7.75-8.35s, even 8.35-8.95s, slowing to a stop at 9.25s) and hand the glide over to a camera that holds the page's bottom edge at that 42px line from 8.3 to 8.65s. Dive: log scale on a quadratic ease in-out, then solve the look-at point from the pinned edge. A rounded-rect mask morphs from the full page to the hero, 24px to 38px corners. 7. Render with Playwright on the real GPU (--use-angle=d3d11 --enable-gpu --ignore-gpu-blocklist): 60fps, 16 subframes across 0.7 of a frame for motion blur, H.264 MP4. The track's hit goes on 9.97s, whooshes on 8.66 and 9.80. If you can't run code on my computer, tell me straight away that you can only make a live preview here and that the MP4 needs Claude Code. Phones or cards that fade out with transparency show whatever is behind them, so fade them into the haze colour first and only cut to transparent at the very end. Keep most lifts tiny (20-40px) and lock the page before timing anything, because any change in a section's height shifts everything after it. Before the final render, measure a quick 30fps preview with optical flow: the speed down the page must never dip and the zoom must never turn into a zoom-in during the flight. Ask me for the inputs, capture my page, then show me stills at 0, 1.6, 2.5, 5, 6.5, 9.3 and 11 seconds before you render.

send your landing page to claude with this prompt ull get a video like this, made with code for free thank me later ↓ Ask me for: my landing page link, my brand name and logo mark, a two-part closing line (a statement, then a short italic tail), and a 15 second track (optional). A 14.5 second 3D fly-over of my landing page, 1440x1152 at 60fps. The page lies flat on a bright studio floor (#f9fbfb in the middle, #f2f3f6 in the corners) with a soft wide shadow around it and 24px rounded corners. One continuous camera, never a cut: it starts low over the hero and glides backwards down the page at one steady speed while looking up it, rises straight overhead to show the whole page as one strip, dives into the hero and lands it as a card under a two-line title. Focus is razor thin in front of the subject and almost none behind it, so everything near the lens melts. Cards float a little above the page with soft shadows; photos, chips and the testimonial lift off and stand up toward the lens as the camera passes them. Four small tiles of my logo lift off beside the hero button and stay with the film until the end card. The title is Geist 500, the italic tail Instrument Serif. Banned: cuts, crossfades, stops or surges in the glide, the camera turning or swinging sideways, zooming in and back out, glows, any text laid over the page before the end card. 14.5 seconds: flight 0-8.2s, rise 7.75-9.25s, overhead 9.25-9.47s, dive 9.47-9.97s, title card 9.97-14.5s. The camera 56° off straight-down and 1360px from the point it looks at, centred on the top half of the hero, the phone or product mockup sharp, four 32px logo tiles beside the button → 0-0.6: the glide eases in from rest → 0.1-1.35: the tiles lift, grow to 140-200px and hang just outside the page's top corners while the hero's chips rise to 60-80px and stand up 30° → 1.25-1.6: the glide doubles to cruising speed as the hero falls behind → 1.6: the second section's title passes the centre of the frame, its photos blurred near the lens → 1.35-2.7: that section's main photos lift to 100-130px and stand up 46°, two of its chips fly up to about 200px, stand up 54° and pass the left and right edges at 2.5 → 1.2-2.4: the tiles trail the camera 300px down the page, then drift out of the top → 3.0-7.3: every following section passes through at the same steady speed, each one sharp as it crosses the middle of the frame and soft below it; a logo tile drifts past the left edge close and blurred at 5.4 → 5.45-6.3: the testimonial card rises from 22 to 112px, stands up 30° and shows a 34px white edge → 7.3-8.2: the glide eases off as the footer arrives, the footer title sharp at 8.0 → 7.75-9.25: the rise, zooming out at an even rate while the tilt flattens (8.15-8.95) and the page's bottom edge settles 42px above the frame bottom → 9.25-9.47: the whole page as one centred strip, creeping 3.5% closer → 9.47-9.97: the dive, the page's top edge pinned to the frame top while it grows, everything below the hero fading out, then the top drops to y 283 so the hero lands as a 1018px wide card with 38px corners and a soft shadow; two logo tiles sit on its top corners, one crisp at the right edge, two huge soft blurs drift in at the bottom corners → 10.02: a white badge pill (logo + brand, 21px) fades in at y 44 → 10.12: line 1 at 74px, one word every 0.06s → 10.36: the italic tail at 82px in grey #8b8b92, one word every 0.05s, each word rising 16px out of a 12px blur in 0.34s → 10.6-14.5: hold, the card creeping 2% closer, the tiles drifting a few px. 1. Open my link in headless Chromium (Playwright) at 1440px wide, device scale 2, and scroll to the bottom once so lazy images and scroll animations finish. Mark the pieces that lift (cards, phone or product mockups, chips, feature photos, the testimonial, the hero button) with data-layer. Screenshot the full page with them hidden, then each piece alone on a transparent background with 28px padding, and save every piece's page position to a JSON. 2. One WebGL2 film page, 1440x1152, every frame computed from time inside seek(t): no timers, no CSS transitions. The page is a textured quad on the floor and each piece its own quad at its height, drawn lowest first with no depth buffer. Use mipmaps and 16x anisotropic filtering or the far text shimmers. 3. Drive the camera from one speed curve, never from a position key every half second. Focal length 1880px, 56° tilt, distance easing out from 1360 to 1700px and never back in, no turning. Speed down the page as a share of cruise (cruise is about 770 page px/s): 0 at 0s, 0.5 by 0.6s, held at 0.5 to 1.25s, 1.0 by 1.6s, held between 0.94 and 1.1 to 7.3s, then easing to 0.12 by 8.3s. Integrate it into the page position. 4. Depth of field per pixel: blur radius = 75 x (focus - depth) / depth in front of the focus and 6 x (depth - focus) / depth behind it, capped at 120px, 40 taps on a golden-angle disc, each tap read from a mip level matched to the blur. Keep the focus on whatever crosses the middle of the frame. 5. A lifted piece stands up by turning about its own middle, top edge rising toward the lens. Each casts a shadow on whatever is under it: the same picture in flat #1a2133, offset (0.10z, 4 + 0.36z), blurred 7 + 0.5z, 26% opacity. 6. Rise: zoom out in log scale with a smooth trapezoid speed (speeding up 7.75-8.35s, even 8.35-8.95s, slowing to a stop at 9.25s) and hand the glide over to a camera that holds the page's bottom edge at that 42px line from 8.3 to 8.65s. Dive: log scale on a quadratic ease in-out, then solve the look-at point from the pinned edge. A rounded-rect mask morphs from the full page to the hero, 24px to 38px corners. 7. Render with Playwright on the real GPU (--use-angle=d3d11 --enable-gpu --ignore-gpu-blocklist): 60fps, 16 subframes across 0.7 of a frame for motion blur, H.264 MP4. The track's hit goes on 9.97s, whooshes on 8.66 and 9.80. If you can't run code on my computer, tell me straight away that you can only make a live preview here and that the MP4 needs Claude Code. Phones or cards that fade out with transparency show whatever is behind them, so fade them into the haze colour first and only cut to transparent at the very end. Keep most lifts tiny (20-40px) and lock the page before timing anything, because any change in a section's height shifts everything after it. Before the final render, measure a quick 30fps preview with optical flow: the speed down the page must never dip and the zoom must never turn into a zoom-in during the flight. Ask me for the inputs, capture my page, then show me stills at 0, 1.6, 2.5, 5, 6.5, 9.3 and 11 seconds before you render.

141,534 次观看

daily reminder of how cooked we are one of these is a real creator, the other is an ai replica can you guess which one? prompt below

daily reminder of how cooked we are one of these is a real creator, the other is an ai replica can you guess which one? prompt below

184,495 次观看

if you want to learn how i make launch videos like this bookmark the article below

if you want to learn how i make launch videos like this bookmark the article below

88,250 次观看

fable 5 is INSANE for ugc ads i put every prompt behind our hyper realistic ai ads into one skills library. built from 1,855 viral ads scanned, 1,204 rejected, 61 winners reverse engineered every girl in this video came out of it. not one of them is real. under $1.20 an ad, under 15 minutes inside the library: the character lock that holds one face across every cut the voice formula that never drifts between scenes the anti ai negative stack that kills the "ai look" the full 8 beat ad template. fill the brackets, render a ugc creator charges $300-500 for ONE of these videos comment "PROMPTS" and ill dm you the full library (follow so i can dm)

fable 5 is INSANE for ugc ads i put every prompt behind our hyper realistic ai ads into one skills library. built from 1,855 viral ads scanned, 1,204 rejected, 61 winners reverse engineered every girl in this video came out of it. not one of them is real. under $1.20 an ad, under 15 minutes inside the library: the character lock that holds one face across every cut the voice formula that never drifts between scenes the anti ai negative stack that kills the "ai look" the full 8 beat ad template. fill the brackets, render a ugc creator charges $300-500 for ONE of these videos comment "PROMPTS" and ill dm you the full library (follow so i can dm)

427,095 次观看

INTRODUCING: GPT 6-ASTRA for marketing just kidding. i'm giving this away for free, runs locally on your device with one sentence you take one winning ad and make 50+ variations of it different faces, hooks, and angles for your business run the same campaign budget across all 50 instead of betting it on 1 video and calling it a flop download it here for free: (this video was made by gpt astra as well btw, prompt in the comments)

INTRODUCING: GPT 6-ASTRA for marketing just kidding. i'm giving this away for free, runs locally on your device with one sentence you take one winning ad and make 50+ variations of it different faces, hooks, and angles for your business run the same campaign budget across all 50 instead of betting it on 1 video and calling it a flop download it here for free: (this video was made by gpt astra as well btw, prompt in the comments)

10,698 次观看

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

OPUS 5.5 IS THE ONLY MOTION DESIGNER YOU NEED this launch video cost $0 and is pure code everyone else on X claims the same shit, then sends you to their website or mcp this is completely free with 0 external tools steal the prompt and try it in your claude ↓ Ask me for: a one-word brand name for the wordmark (a verb works best), 9 to 12 high-res photos, a royalty-free song around 120 BPM with a drop and a quiet breakdown (Mixkit, free for commercial use), and a free stock clip of a plain wall with moving plant shadows (Pexels). An Apple-keynote launch film, 2D only, one continuous take. Every scene is made out of the previous one: nothing fades, blurs or cuts. Objects change shape instead: text rises out of a mask line, icons pop from zero on a spring, bars draw across, pages push, and a black shape floods the whole frame and contracts into the next scene. Warm off-white canvas, black UI, iOS 26 liquid glass over the photos. Archivo (wdth 125, weight 800) for the wordmark, Geist for UI. A cursor drives every change with real clicks, drags and long-presses. The camera zooms screen-studio style so each moment fills the square, and the cursor scales with it. Banned: crossfades, blur-ins, brightness "developing", 3D flips, particles, glows, holds longer than 1s, anything that looks like a template. 120 BPM, 54 beats, something happens on every beat. Open: the wordmark squeezes into its own period like an accordion, the dot grows into a black pill, a label rises inside it. Click: six iris blades close over the label and snap open onto a photo. The circle becomes a square, shrinks, the grid unfolds from behind it like a paper map (center, plus, corners), reflows into a bento, and a click zooms into one tile, landing exactly on the drop. Glass: a glass word pops in letter by letter, melts into a droplet that stretches into a glass toolbar. The adjust icon turns it into a slider. Dragging relights the photo from day to golden hour (two aligned shots), and the knob turns into a glass lens while held. It lifts into a glass orb, the next photo opens inside it as a circle, and the orb expands into a lock screen: glass clock digits, date, and a home bar that stretches into a glass music player. Stage: the lock screen pulls back into a phone (the bezel grows out of the screen edge). The Dynamic Island stretches like liquid, pinches off, flies over and grows into a Mac window that rolls up like a blind. Long-press the wallpaper, drag it onto a Safari tab, the page pushes in, drop it and it becomes the hero of a landing page. Scroll: the hero morphs into a framed print on a product card, with the mat and molding growing out of the photo's edge. Pick a frame color (it paints across) and a size, then the nav button flies down into "Order print". Order: one black shape keeps morphing: Ordered ✓ → Printing % → On its way (a van on a route) → Delivered ✓. Wall: the delivered circle floods the frame edge to edge, holds black for a beat, and contracts into the framed print hanging on the real wall footage. The same iris opens onto the print, closes again, the frame floods the screen and contracts into the pill → the dot → the letters spring back out, landing on the beat return. Last frame = first frame. 1. One HTML file, square 1440x1440. Every style is computed from time inside an async seek(t): no CSS transitions, no timers, no state between frames. 2. Springs are closed-form step responses. A value with many targets is the sum of one spring per change, so it stays a pure function of time. 3. Liquid glass: each glass element holds its own clone of the scene behind it, filtered with an SVG feImage displacement map (a rounded-rect distance field) through three feDisplacementMaps at slightly different scales for chromatic edges, plus a rim light. Glass letters: a canvas distance field per glyph gives the map, mask and highlights. 4. Goo: blur + alpha threshold, then composite the source atop it so the glass stays sharp inside. 5. Iris: 6 blades around a hexagonal aperture. Each blade is its two vertices, both edge extensions and the SHORT arc between them. 6. Wordmark squeeze: every letter moves toward the dot by the same factor and its drawn width follows (narrow the wdth axis, scale the rest), so the letters stay touching. 7. Footage: re-encode all-intra (ffmpeg -g 1), load it as a blob URL, await 'seeked' before drawing each frame. 8. Sound: a downloaded SFX for every event (Mixkit), never synthesized, each placed by its measured peak. The song starts on a downbeat: the zoom lands on the drop, the wall sits in the breakdown, the wordmark returns with the beat. Loudnorm to -14 LUFS. 9. Render with Playwright: 4 subframes per frame blended with ffmpeg tmix, 60fps. Check one frame per beat, then scan for single-frame pops (frame-difference spikes 3x their neighbours). backdrop-filter: url() misreads displacement maps in Chromium, so clone the scene instead. A flood must overscale past the corners and take about 0.3s, or half the screen changes in one frame. A child with visibility: visible shows through a hidden parent, so use inherit. Text that swaps inside a morphing shape needs its own mask. python http.server can't range-seek video, so use the blob URL. Ask me for the inputs, then show me the beat map and 4 stills (open, glass, stage, wall) before you write the full film.
0:29
twoclipping's profile picture

OPUS 5.5 IS THE ONLY MOTION DESIGNER YOU NEED this launch video cost $0 and is pure code everyone else on X claims the same shit, then sends you to their website or mcp this is completely free with 0 external tools steal the prompt and try it in your claude ↓ Ask me for: a one-word brand name for the wordmark (a verb works best), 9 to 12 high-res photos, a royalty-free song around 120 BPM with a drop and a quiet breakdown (Mixkit, free for commercial use), and a free stock clip of a plain wall with moving plant shadows (Pexels). An Apple-keynote launch film, 2D only, one continuous take. Every scene is made out of the previous one: nothing fades, blurs or cuts. Objects change shape instead: text rises out of a mask line, icons pop from zero on a spring, bars draw across, pages push, and a black shape floods the whole frame and contracts into the next scene. Warm off-white canvas, black UI, iOS 26 liquid glass over the photos. Archivo (wdth 125, weight 800) for the wordmark, Geist for UI. A cursor drives every change with real clicks, drags and long-presses. The camera zooms screen-studio style so each moment fills the square, and the cursor scales with it. Banned: crossfades, blur-ins, brightness "developing", 3D flips, particles, glows, holds longer than 1s, anything that looks like a template. 120 BPM, 54 beats, something happens on every beat. Open: the wordmark squeezes into its own period like an accordion, the dot grows into a black pill, a label rises inside it. Click: six iris blades close over the label and snap open onto a photo. The circle becomes a square, shrinks, the grid unfolds from behind it like a paper map (center, plus, corners), reflows into a bento, and a click zooms into one tile, landing exactly on the drop. Glass: a glass word pops in letter by letter, melts into a droplet that stretches into a glass toolbar. The adjust icon turns it into a slider. Dragging relights the photo from day to golden hour (two aligned shots), and the knob turns into a glass lens while held. It lifts into a glass orb, the next photo opens inside it as a circle, and the orb expands into a lock screen: glass clock digits, date, and a home bar that stretches into a glass music player. Stage: the lock screen pulls back into a phone (the bezel grows out of the screen edge). The Dynamic Island stretches like liquid, pinches off, flies over and grows into a Mac window that rolls up like a blind. Long-press the wallpaper, drag it onto a Safari tab, the page pushes in, drop it and it becomes the hero of a landing page. Scroll: the hero morphs into a framed print on a product card, with the mat and molding growing out of the photo's edge. Pick a frame color (it paints across) and a size, then the nav button flies down into "Order print". Order: one black shape keeps morphing: Ordered ✓ → Printing % → On its way (a van on a route) → Delivered ✓. Wall: the delivered circle floods the frame edge to edge, holds black for a beat, and contracts into the framed print hanging on the real wall footage. The same iris opens onto the print, closes again, the frame floods the screen and contracts into the pill → the dot → the letters spring back out, landing on the beat return. Last frame = first frame. 1. One HTML file, square 1440x1440. Every style is computed from time inside an async seek(t): no CSS transitions, no timers, no state between frames. 2. Springs are closed-form step responses. A value with many targets is the sum of one spring per change, so it stays a pure function of time. 3. Liquid glass: each glass element holds its own clone of the scene behind it, filtered with an SVG feImage displacement map (a rounded-rect distance field) through three feDisplacementMaps at slightly different scales for chromatic edges, plus a rim light. Glass letters: a canvas distance field per glyph gives the map, mask and highlights. 4. Goo: blur + alpha threshold, then composite the source atop it so the glass stays sharp inside. 5. Iris: 6 blades around a hexagonal aperture. Each blade is its two vertices, both edge extensions and the SHORT arc between them. 6. Wordmark squeeze: every letter moves toward the dot by the same factor and its drawn width follows (narrow the wdth axis, scale the rest), so the letters stay touching. 7. Footage: re-encode all-intra (ffmpeg -g 1), load it as a blob URL, await 'seeked' before drawing each frame. 8. Sound: a downloaded SFX for every event (Mixkit), never synthesized, each placed by its measured peak. The song starts on a downbeat: the zoom lands on the drop, the wall sits in the breakdown, the wordmark returns with the beat. Loudnorm to -14 LUFS. 9. Render with Playwright: 4 subframes per frame blended with ffmpeg tmix, 60fps. Check one frame per beat, then scan for single-frame pops (frame-difference spikes 3x their neighbours). backdrop-filter: url() misreads displacement maps in Chromium, so clone the scene instead. A flood must overscale past the corners and take about 0.3s, or half the screen changes in one frame. A child with visibility: visible shows through a hidden parent, so use inherit. Text that swaps inside a morphing shape needs its own mask. python http.server can't range-seek video, so use the blob URL. Ask me for the inputs, then show me the beat map and 4 stills (open, glass, stage, wall) before you write the full film.

zero

139,851 次观看 • 21 天前

this is my best project yet and its fucking insane a studio would charge you $2k+ for this this cost me basically $0 and its all pure code from opus 5.5 the prompt doesnt even need a single mcp tool steal it and drop your brand in ↓ Ask me for: my product's name, a one-line pitch, my logo, 3-6 screenshots of my product, 40+ images of what it makes (or photos of it), my brand colours and font, an ElevenLabs API key and voice ID, and a royalty-free song with a clear drop (the file and the drop's timestamp). If I skip any, use the defaults: "Ora 2", "an image model made for taste", free Unsplash and Pixabay images, Geist, ink #111214, the voice Samara X (19STyYD15bswVz51nqLf) on eleven_v4, and Pixabay "Cascade Breathe" (129.83 BPM, drop at 75.39s). Write a 9-line voiceover in this shape and map every line to my product: "This is [name]. A [category]... made for [value]. [Verb] in ANY style. Show it a [input] — and it just... gets you. The more you use it, the BETTER it gets. Tune its [setting]. Its [setting]. Its [setting]. Every [output] — exactly how you see it. [Name]. Out now." Light emotion tags only: [softly] on the quiet lines, [excited] on the [Verb] line. The opener gets no tag and a plain full stop. Call the ElevenLabs API directly with my key, no MCP. Generate 4 takes of the whole script in one read and let me pick. If one line is off, regenerate only that line 4 times and splice the best one into my take. Cut every pause over 0.28s down to 0.2s, then level each phrase 85% of the way to the median level, changing gain only inside the pauses. For word timings, cut the read at every pause of 100ms or more, transcribe each chunk on its own with Whisper and pin each chunk's first word to its measured onset. One Whisper pass puts words up to half a second late. A 22 second square launch film, 1440x1440 at 60fps, in the style of an AI lab's launch: a white page, one typeface, black ink, real images, and every caption typed word by word at the exact moment it's spoken. Every control (the prompt bar, the settings panel, the caption pill) is liquid glass: the scene behind it frosted, its edge bending that scene like thick glass, a top sheen, a bright rim and a soft lift shadow. Glass on plain white shows nothing, so put a slow pastel aura in my brand colours, or a blurred wash of the photo, behind it. The one word she stresses types in a gradient of my brand colours with a faint glow behind it. Motion rules: the camera always drifts (a 1.0 to 1.04 push per scene, and when one scene hands its content to the next, the next starts at the zoom the last one ended on), nothing pops in (fades of at least 0.3s, eased), images switch on 16th notes with a click each, scene changes land on phrase starts, and the music's drop lands on the [Verb] line. No full stops on screen. Banned: selection-box highlights, beat-snapped slams, white flashes, 3D, templates. Seven scenes, each hung on the voice: 1. "This is [name]": a collage of my images drifts out as the name types in big, then the category line replaces it. 2. "made for [value]": full-bleed flashes of my best images on 16th notes into the drop, with the line typed over them in white. 3. The drop: a glass prompt bar types a short prompt, then the result card switches style on every 16th, with a black style chip that rolls to each new name and a strip of thumbnails. 4. "Show it a moodboard": 9 images fly into a 3x3 grid, then ring around the result as "It gets you" types. 5. "The more you use it, the better it gets": two typed lines, the stressed word in the gradient. 6. The settings: a glass panel of 3 sliders, each moving as she names it. The picture shifts hue, rolls new seeds on 16ths, then turns poster, and a blurred wash of its own colours shifts with it behind the glass. 7. "Every [output], exactly how you see it": 120 of my images burst from the centre behind a glass caption pill, then collapse into my logo as the name types, with "Out now" underneath. Hold 2s. Swap the prompt bar, the results and the sliders for my product's real input, outputs and settings. Start the song so its drop lands on the [Verb] line, and anchor the beat grid there. Duck the music under the voice with a 3-band sidechain (lows 30%, mids 85%, air 55%; 0.3s hold, 50ms look-ahead, 0.5s release), then move each phrase's mids until the voice sits about 9 dB over the music between 300 Hz and 4 kHz. One downloaded Mixkit SFX per event, placed by its measured peak: a click on every image switch, a key on every typed letter, a soft landing on the stressed word, whooshes, and impacts on the drop and the logo, trimmed around their peak (many are 4 second risers). Fade the music on a dB curve under the end card. Loudnorm to -14 LUFS. 1. One HTML canvas. Every frame is a pure function of time inside seek(t), and every caption and cut reads the word table. 2. The glass: snapshot the canvas behind the shape, blur it about 14px for the body, draw a lightly blurred copy magnified about 1.06x in a 12px band along the edge, then add the milk, sheen, rim and shadow. 3. Render with Playwright at 60fps with 8 motion-blur subframes, then encode with ffmpeg. 4. Before you show me anything: a contact sheet of stills, a frame-diff scan for single-frame pops (only the 16th-note runs may jump), and the voice-over-music ratio for every phrase. A [warmly] opener comes out whispered and [excited] sounds fake. A highlight box behind a word looks like a Windows text selection. If a scene's camera restarts at 1.0 mid-handoff, the zoom snaps. A 0.05s fade reads as a pop-in. Ask me for the inputs, write the script, send me 4 voice takes to pick, then show me 8 stills before the full render.
0:21
twoclipping's profile picture

this is my best project yet and its fucking insane a studio would charge you $2k+ for this this cost me basically $0 and its all pure code from opus 5.5 the prompt doesnt even need a single mcp tool steal it and drop your brand in ↓ Ask me for: my product's name, a one-line pitch, my logo, 3-6 screenshots of my product, 40+ images of what it makes (or photos of it), my brand colours and font, an ElevenLabs API key and voice ID, and a royalty-free song with a clear drop (the file and the drop's timestamp). If I skip any, use the defaults: "Ora 2", "an image model made for taste", free Unsplash and Pixabay images, Geist, ink #111214, the voice Samara X (19STyYD15bswVz51nqLf) on eleven_v4, and Pixabay "Cascade Breathe" (129.83 BPM, drop at 75.39s). Write a 9-line voiceover in this shape and map every line to my product: "This is [name]. A [category]... made for [value]. [Verb] in ANY style. Show it a [input] — and it just... gets you. The more you use it, the BETTER it gets. Tune its [setting]. Its [setting]. Its [setting]. Every [output] — exactly how you see it. [Name]. Out now." Light emotion tags only: [softly] on the quiet lines, [excited] on the [Verb] line. The opener gets no tag and a plain full stop. Call the ElevenLabs API directly with my key, no MCP. Generate 4 takes of the whole script in one read and let me pick. If one line is off, regenerate only that line 4 times and splice the best one into my take. Cut every pause over 0.28s down to 0.2s, then level each phrase 85% of the way to the median level, changing gain only inside the pauses. For word timings, cut the read at every pause of 100ms or more, transcribe each chunk on its own with Whisper and pin each chunk's first word to its measured onset. One Whisper pass puts words up to half a second late. A 22 second square launch film, 1440x1440 at 60fps, in the style of an AI lab's launch: a white page, one typeface, black ink, real images, and every caption typed word by word at the exact moment it's spoken. Every control (the prompt bar, the settings panel, the caption pill) is liquid glass: the scene behind it frosted, its edge bending that scene like thick glass, a top sheen, a bright rim and a soft lift shadow. Glass on plain white shows nothing, so put a slow pastel aura in my brand colours, or a blurred wash of the photo, behind it. The one word she stresses types in a gradient of my brand colours with a faint glow behind it. Motion rules: the camera always drifts (a 1.0 to 1.04 push per scene, and when one scene hands its content to the next, the next starts at the zoom the last one ended on), nothing pops in (fades of at least 0.3s, eased), images switch on 16th notes with a click each, scene changes land on phrase starts, and the music's drop lands on the [Verb] line. No full stops on screen. Banned: selection-box highlights, beat-snapped slams, white flashes, 3D, templates. Seven scenes, each hung on the voice: 1. "This is [name]": a collage of my images drifts out as the name types in big, then the category line replaces it. 2. "made for [value]": full-bleed flashes of my best images on 16th notes into the drop, with the line typed over them in white. 3. The drop: a glass prompt bar types a short prompt, then the result card switches style on every 16th, with a black style chip that rolls to each new name and a strip of thumbnails. 4. "Show it a moodboard": 9 images fly into a 3x3 grid, then ring around the result as "It gets you" types. 5. "The more you use it, the better it gets": two typed lines, the stressed word in the gradient. 6. The settings: a glass panel of 3 sliders, each moving as she names it. The picture shifts hue, rolls new seeds on 16ths, then turns poster, and a blurred wash of its own colours shifts with it behind the glass. 7. "Every [output], exactly how you see it": 120 of my images burst from the centre behind a glass caption pill, then collapse into my logo as the name types, with "Out now" underneath. Hold 2s. Swap the prompt bar, the results and the sliders for my product's real input, outputs and settings. Start the song so its drop lands on the [Verb] line, and anchor the beat grid there. Duck the music under the voice with a 3-band sidechain (lows 30%, mids 85%, air 55%; 0.3s hold, 50ms look-ahead, 0.5s release), then move each phrase's mids until the voice sits about 9 dB over the music between 300 Hz and 4 kHz. One downloaded Mixkit SFX per event, placed by its measured peak: a click on every image switch, a key on every typed letter, a soft landing on the stressed word, whooshes, and impacts on the drop and the logo, trimmed around their peak (many are 4 second risers). Fade the music on a dB curve under the end card. Loudnorm to -14 LUFS. 1. One HTML canvas. Every frame is a pure function of time inside seek(t), and every caption and cut reads the word table. 2. The glass: snapshot the canvas behind the shape, blur it about 14px for the body, draw a lightly blurred copy magnified about 1.06x in a 12px band along the edge, then add the milk, sheen, rim and shadow. 3. Render with Playwright at 60fps with 8 motion-blur subframes, then encode with ffmpeg. 4. Before you show me anything: a contact sheet of stills, a frame-diff scan for single-frame pops (only the 16th-note runs may jump), and the voice-over-music ratio for every phrase. A [warmly] opener comes out whispered and [excited] sounds fake. A highlight box behind a word looks like a Windows text selection. If a scene's camera restarts at 1.0 mid-handoff, the zoom snaps. A 0.05s fade reads as a pop-in. Ask me for the inputs, write the script, send me 4 voice takes to pick, then show me 8 stills before the full render.

zero

40,241 次观看 • 14 天前

STOP PAYING FOR MOTION DESIGN SOFTWARE opus 5.5 one shot every frame of this in code, no after effects im open sourcing the whole template for free plug in your product and it recreates this steal the prompt ↓ Ask me for: the one question a user asks my product and its one-line answer, two album covers, a royalty-free song around 110 BPM with a quiet intro and a hard drop (Mixkit, free for commercial use), and my logo for the ending. If I skip any, use the defaults: "is this all code?" / "yes. every frame.", two atmospheric photos, Mixkit "Head Bang". A 22 second square loop, 1440x1440 at 60fps, 2D only, one continuous take. Nothing ever cuts: every scene grows out of the last, and every gesture physically carries the camera into the next world. Every morph glides for 0.8s on cubic-bezier(.45,0,.15,1) and the camera zoom rides the same curve, so shapes change so smoothly you barely notice. Content dissolves in the back half of each glide. One gesture per scene. Look: a warm light stage (#f3f3f0 to #e3e3de), black UI, the app world dark (#121212) tinted from the current album cover, one green accent (#1ed760). Geist for UI, the real macOS pointer, soft layered shadows that grow with the shape's height. Banned: hard cuts, bouncy springs, particles, glows, zooming in and straight back out, holds longer than 1s, anything that looks like a template. Beats are the song's, and the press lands on its drop. Generate: the cursor clicks, the pill glides into a spinner, then a check. Chat: the check splits into three typing dots (goo). The left dot flies up into the question bubble and types it, the right one flies down into the reply. Both contract back into dots while gliding in and pour into the middle one. Play: the middle dot bends into a play triangle, point by point. The cursor presses it on the drop: a white button pops in under the click and the dark app floods out around it, so the leftover white becomes the play button. The camera pulls back to reveal the full now-playing screen: big cover, title, heart (liked, fills green), progress, controls, volume. Swipe: the cursor drags the cover sideways, the next track slides in, and the whole app retints from the new cover. Drag: the camera glides to the volume. The cursor drags it to max and keeps pulling: the bar rubber-bands and drags the camera sideways out of the app, tracking the knob across a dark dotted canvas. Chart: the line lands and bends up into a green chart while the number counts up. The volume knob becomes its last point. Dive: the cursor clicks that point and the camera dives into it until the light stage fills the frame. Ending: an "Ask [my product]" button grows out of the light, thins into a line, and the line fans out into my logo (default: the Claude spark, six copies rotating into twelve rays in Claude orange). It folds back into the line, which thickens into Generate. Last frame = first frame. 1. One HTML canvas. Everything is a pure function of time inside seek(t): no timers, no state between frames. 2. A camera with position and log-space zoom. Scenes live side by side in one world, so a pan really travels. 3. Goo: blur + alpha threshold on an offscreen layer for the split and the merges. 4. Floods are circles that grow from whatever caused them to the farthest corner in about 0.4s, and the colour switch happens underneath them. 5. Sound: before the press the song plays through a low-pass filter, like it's in the next room, and opens up to full on the drop. A downloaded Mixkit SFX for every event, each placed by its measured peak. Loudnorm to -14 LUFS. 6. Render with Playwright at 60fps with 4 motion-blur subframes, 12 on the fast pan. Then scan every frame for single-frame jumps and fix each one. A handoff between two drawings only works once the first one has fully landed, or it pops. The cursor must stay on whatever it drags, even while it stretches. A counter or tooltip that changes every frame smears under motion blur, so swap whole values. Ask me for the inputs, then show me the beat map and 6 stills (chat, play, app, drag, chart, logo) before you render.
0:22
twoclipping's profile picture

STOP PAYING FOR MOTION DESIGN SOFTWARE opus 5.5 one shot every frame of this in code, no after effects im open sourcing the whole template for free plug in your product and it recreates this steal the prompt ↓ Ask me for: the one question a user asks my product and its one-line answer, two album covers, a royalty-free song around 110 BPM with a quiet intro and a hard drop (Mixkit, free for commercial use), and my logo for the ending. If I skip any, use the defaults: "is this all code?" / "yes. every frame.", two atmospheric photos, Mixkit "Head Bang". A 22 second square loop, 1440x1440 at 60fps, 2D only, one continuous take. Nothing ever cuts: every scene grows out of the last, and every gesture physically carries the camera into the next world. Every morph glides for 0.8s on cubic-bezier(.45,0,.15,1) and the camera zoom rides the same curve, so shapes change so smoothly you barely notice. Content dissolves in the back half of each glide. One gesture per scene. Look: a warm light stage (#f3f3f0 to #e3e3de), black UI, the app world dark (#121212) tinted from the current album cover, one green accent (#1ed760). Geist for UI, the real macOS pointer, soft layered shadows that grow with the shape's height. Banned: hard cuts, bouncy springs, particles, glows, zooming in and straight back out, holds longer than 1s, anything that looks like a template. Beats are the song's, and the press lands on its drop. Generate: the cursor clicks, the pill glides into a spinner, then a check. Chat: the check splits into three typing dots (goo). The left dot flies up into the question bubble and types it, the right one flies down into the reply. Both contract back into dots while gliding in and pour into the middle one. Play: the middle dot bends into a play triangle, point by point. The cursor presses it on the drop: a white button pops in under the click and the dark app floods out around it, so the leftover white becomes the play button. The camera pulls back to reveal the full now-playing screen: big cover, title, heart (liked, fills green), progress, controls, volume. Swipe: the cursor drags the cover sideways, the next track slides in, and the whole app retints from the new cover. Drag: the camera glides to the volume. The cursor drags it to max and keeps pulling: the bar rubber-bands and drags the camera sideways out of the app, tracking the knob across a dark dotted canvas. Chart: the line lands and bends up into a green chart while the number counts up. The volume knob becomes its last point. Dive: the cursor clicks that point and the camera dives into it until the light stage fills the frame. Ending: an "Ask [my product]" button grows out of the light, thins into a line, and the line fans out into my logo (default: the Claude spark, six copies rotating into twelve rays in Claude orange). It folds back into the line, which thickens into Generate. Last frame = first frame. 1. One HTML canvas. Everything is a pure function of time inside seek(t): no timers, no state between frames. 2. A camera with position and log-space zoom. Scenes live side by side in one world, so a pan really travels. 3. Goo: blur + alpha threshold on an offscreen layer for the split and the merges. 4. Floods are circles that grow from whatever caused them to the farthest corner in about 0.4s, and the colour switch happens underneath them. 5. Sound: before the press the song plays through a low-pass filter, like it's in the next room, and opens up to full on the drop. A downloaded Mixkit SFX for every event, each placed by its measured peak. Loudnorm to -14 LUFS. 6. Render with Playwright at 60fps with 4 motion-blur subframes, 12 on the fast pan. Then scan every frame for single-frame jumps and fix each one. A handoff between two drawings only works once the first one has fully landed, or it pops. The cursor must stay on whatever it drags, even while it stretches. A counter or tooltip that changes every frame smears under motion blur, so swap whole values. Ask me for the inputs, then show me the beat map and 6 stills (chat, play, app, drag, chart, logo) before you render.

zero

47,922 次观看 • 19 天前

"visualize the biggest scam in humanity, no words allowed" opus 5.5 came back with this ↓
1:43
twoclipping's profile picture

"visualize the biggest scam in humanity, no words allowed" opus 5.5 came back with this ↓

zero

33,966 次观看 • 15 天前

ByteDance released an official Seedance 2.5 prompt guide and most people still don't know it exists i turned the whole thing into a Claude skill by the time Seedance 2.5 hits every platform your claude will already be an expert at every prompting style the official ByteDance team uses, while everyone else starts from zero 30 seconds to install, then you just describe what you want • ultra realistic travel vlogs, same face in every location • cinematics that hold 4 characters without drifting • meta ads that don't read as AI • swap the product in a winning ad, every cut identical • bullet time, FPV, one-take, dolly zoom, all named in the spec 23 task types, 67 templates, straight from ByteDance and sitting inside your claude comment 'SEEDANCE' and ill send you the skill i built (must be following so the dm goes through)
0:24
twoclipping's profile picture

ByteDance released an official Seedance 2.5 prompt guide and most people still don't know it exists i turned the whole thing into a Claude skill by the time Seedance 2.5 hits every platform your claude will already be an expert at every prompting style the official ByteDance team uses, while everyone else starts from zero 30 seconds to install, then you just describe what you want • ultra realistic travel vlogs, same face in every location • cinematics that hold 4 characters without drifting • meta ads that don't read as AI • swap the product in a winning ad, every cut identical • bullet time, FPV, one-take, dolly zoom, all named in the spec 23 task types, 67 templates, straight from ByteDance and sitting inside your claude comment 'SEEDANCE' and ill send you the skill i built (must be following so the dm goes through)

zero

131,714 次观看 • 2 个月前

opus 5.5 is f*cking insane at motion design every frame is code with 0 external tools im open sourcing the template for all these morph transitions steal it ↓ Ask me for: my product's name (one lowercase word, it becomes a black wordmark with a period), the one job a user hands it before bed, the three results it reports by morning, two photos of the same place at night and by day (aligned, so a crossfade reads as a real sunrise), one sunny daytime photo for outside the logo, and a song with a big hit near its start. If I skip any, use the defaults: "nightshift", "book 10 sales calls this week", 200 leads found / 200 emails sent / 10 calls booked. A 24 second square product launch video, 1440x1440 at 60fps, 2D only, one continuous take that loops. The whole video happens inside the period of the wordmark. Outside it's daytime (the sunny photo behind a black wordmark). Inside it's the night photo under iOS-style glass panels (the blurred photo behind each panel, a tint, a rim light). Nothing cuts: every scene grows out of the last, shapes morph, dots fly, colours change under floods. Every morph glides 0.8s on cubic-bezier(.45,0,.15,1) and the camera zoom rides the same curve. Geist, the real macOS pointer, soft shadows that grow with each shape's height. Banned: flat or gradient backgrounds made in code, camera zooms into tiny points, hard cuts, crossfades between scenes, bouncy springs, particles, glows, holds longer than 1s, cropped type. Beats are the song's. The song enters on its big hit as the first pill appears. Open: the letters slide into the period and vanish into it while it glides to the middle. The period opens like an iris onto the night inside it, and "you log off at 6", then "[product] doesn't", roll through one mask line over the night photo. Ask: a glass "Ask [product]" pill springs in. The cursor clicks it, it glides into an input and the job types out. Find: send shrinks the input to a dot that ripples into a 23x15 grid. A scan line sweeps it, 200 dots light up and a counter counts them. Write: the lit dots pour into a glass email composer. A second, purple cursor labelled "[product]" types a personal opener and presses Send, and the counter runs to 200/200. Night: the composer becomes a glass orb with a progress ring. A clock chip swaps 11:42 PM, 3:17 AM, 5:02 AM, 6:59 AM while the sky relights from night to dawn and "while you sleep" rolls in. Results (beat 20): the orb turns black and goo-splits into the three result pills. The checks pop green. Morning: the pills merge into a Dynamic Island that grows into a phone lock screen: the day photo, the date, a big 7:00, the bezel growing out of the screen edge. Three glass notifications stack in, and the cursor taps the first, which opens like iOS. Proof: a week calendar (10 meetings pop in, a hover shows one's time), then a pipeline chart ($48,200 counts up, the line draws, a hover follows it). A black flood from the line's end becomes "Start your night shift →" and the cursor clicks it. Out: the button shrinks into a dot, the whole scene closes down into it like an iris, and the letters slide back out of the period. The tagline rises. Last frame = first frame. 1. One HTML canvas. Everything is a pure function of time inside seek(t): no timers, no state between frames. 2. One element morphs through every state (size, radius, colour, material) from a table of beat times, so retiming is one edit. 3. Render the inside world into an offscreen canvas and reveal it through the period with a circular mask. Never zoom the camera into the dot. 4. Glass: a pre-blurred copy of the photo clipped to the shape, then a tint and a gradient rim. 5. Goo: blur + alpha threshold on an offscreen layer for the split and the merge. 6. Sound: a downloaded SFX for every event, each placed by its measured peak. The song enters on its hit. Loudnorm to -14 LUFS. 7. Render with Playwright at 60fps with 4 motion-blur subframes. Scan every frame for single-frame jumps and fix each one. A camera zoom into an off-centre dot swings sideways and spikes, so open the dot instead. Ease a closing iris by area, not radius, or its first frames jump. A helper that sets globalAlpha must restore the caller's, or fading cards pop. Counters read the frame's time, not the subframe's, or the digits smear. Ask me for the inputs, then show me the beat map and 6 stills (open, find, write, results, phone, out) before you render.
0:23
twoclipping's profile picture

opus 5.5 is f*cking insane at motion design every frame is code with 0 external tools im open sourcing the template for all these morph transitions steal it ↓ Ask me for: my product's name (one lowercase word, it becomes a black wordmark with a period), the one job a user hands it before bed, the three results it reports by morning, two photos of the same place at night and by day (aligned, so a crossfade reads as a real sunrise), one sunny daytime photo for outside the logo, and a song with a big hit near its start. If I skip any, use the defaults: "nightshift", "book 10 sales calls this week", 200 leads found / 200 emails sent / 10 calls booked. A 24 second square product launch video, 1440x1440 at 60fps, 2D only, one continuous take that loops. The whole video happens inside the period of the wordmark. Outside it's daytime (the sunny photo behind a black wordmark). Inside it's the night photo under iOS-style glass panels (the blurred photo behind each panel, a tint, a rim light). Nothing cuts: every scene grows out of the last, shapes morph, dots fly, colours change under floods. Every morph glides 0.8s on cubic-bezier(.45,0,.15,1) and the camera zoom rides the same curve. Geist, the real macOS pointer, soft shadows that grow with each shape's height. Banned: flat or gradient backgrounds made in code, camera zooms into tiny points, hard cuts, crossfades between scenes, bouncy springs, particles, glows, holds longer than 1s, cropped type. Beats are the song's. The song enters on its big hit as the first pill appears. Open: the letters slide into the period and vanish into it while it glides to the middle. The period opens like an iris onto the night inside it, and "you log off at 6", then "[product] doesn't", roll through one mask line over the night photo. Ask: a glass "Ask [product]" pill springs in. The cursor clicks it, it glides into an input and the job types out. Find: send shrinks the input to a dot that ripples into a 23x15 grid. A scan line sweeps it, 200 dots light up and a counter counts them. Write: the lit dots pour into a glass email composer. A second, purple cursor labelled "[product]" types a personal opener and presses Send, and the counter runs to 200/200. Night: the composer becomes a glass orb with a progress ring. A clock chip swaps 11:42 PM, 3:17 AM, 5:02 AM, 6:59 AM while the sky relights from night to dawn and "while you sleep" rolls in. Results (beat 20): the orb turns black and goo-splits into the three result pills. The checks pop green. Morning: the pills merge into a Dynamic Island that grows into a phone lock screen: the day photo, the date, a big 7:00, the bezel growing out of the screen edge. Three glass notifications stack in, and the cursor taps the first, which opens like iOS. Proof: a week calendar (10 meetings pop in, a hover shows one's time), then a pipeline chart ($48,200 counts up, the line draws, a hover follows it). A black flood from the line's end becomes "Start your night shift →" and the cursor clicks it. Out: the button shrinks into a dot, the whole scene closes down into it like an iris, and the letters slide back out of the period. The tagline rises. Last frame = first frame. 1. One HTML canvas. Everything is a pure function of time inside seek(t): no timers, no state between frames. 2. One element morphs through every state (size, radius, colour, material) from a table of beat times, so retiming is one edit. 3. Render the inside world into an offscreen canvas and reveal it through the period with a circular mask. Never zoom the camera into the dot. 4. Glass: a pre-blurred copy of the photo clipped to the shape, then a tint and a gradient rim. 5. Goo: blur + alpha threshold on an offscreen layer for the split and the merge. 6. Sound: a downloaded SFX for every event, each placed by its measured peak. The song enters on its hit. Loudnorm to -14 LUFS. 7. Render with Playwright at 60fps with 4 motion-blur subframes. Scan every frame for single-frame jumps and fix each one. A camera zoom into an off-centre dot swings sideways and spikes, so open the dot instead. Ease a closing iris by area, not radius, or its first frames jump. A helper that sets globalAlpha must restore the caller's, or fading cards pop. Counters read the frame's time, not the subframe's, or the digits smear. Ask me for the inputs, then show me the beat map and 6 stills (open, find, write, results, phone, out) before you render.

zero

12,628 次观看 • 16 天前

没有更多内容可加载