@De_AILab
Joined May 2026
gao2025 ksana retweeted
这次真被 Opus 5.5 震到了,瘫坐在椅子上那种 🤯 最近在 vibe coding 一个 proxy 管理面板,做了几套主题,缺个点阵字体,就顺手让 Opus 5.5 设计一个。 结果它很快交出来一款可变点阵字体,还给自己起了名字叫 PUNCTUM。字重 100–900,圆度 0–100,一共 108 个字形,把圆度从 100 拉到 0,圆点会一点点变成方像素。 它还顺带做了一个很专业的字体样例页,把这个字体放进各种老设备的场景里:电梯的 LED 楼层灯、卡座的 VFD 屏、热敏小票、掌机 LCD、火车站发车牌。 我又跟它来回调了几轮,现在的效果放以前,我觉得得是很厉害的字体工作室才做得出来。视频是它做的字体发布样片。 字体还在继续完善,之后会连同整个制作过程一起开源到 GitHub,有兴趣的可以先关注一下。
23
48
8
586
43,226
gao2025 ksana retweeted
475 Claude Opus 5.5 video demos in one GitHub repo. 🤯 Motion graphics, explainers, 3D scenes, and games built with HTML, Canvas, SVG, and Three.js. Includes shared prompts and links to the original posts, so you can pick a demo and try building it yourself. Repo in the comments.
32
109
2
972
51,734
gao2025 ksana retweeted
🚨 UN TIPO EXPLICA EN 18 MINUTOS COMO CREAR VIDEOS DE IA ILIMITADOS Y GRATIS Este chaval te enseña cómo generar videos con Google Flow y King AI sin gastar en créditos. ¿Te gustaría tener un canal automatizado de Youtube y generar miles de euros al mes pasivamente? Deja ese capítulo de Naruto y ponte a ver este tutorial 🥷 🔖 Guárdalo, vale la pena.
79
546
7
2,783
190,077
gao2025 ksana retweeted
Here are 8 design resources worth bookmarking: 1. jiro.build — 1,200+ design prompts 2. navbar.gallery — navbar inspiration 3. footer.design — better footers 4. cta.gallery — CTA inspiration 5. 404s.design — 404 pages worth seeing 6. unsection.com — ready-made sections 7. bentogrids.com — bento grid ideas 8. 60fps.design — premium motion details Save this list. You’ll need it. 🔖
23
334
6
2,125
123,310
gao2025 ksana retweeted
Today I'm releasing a new skill One that makes your coding agent direct a GOOD launch video/short film. This video below was made with it in a quick short prompt! npx skills add Leonxlnx/cinetic github.com/Leonxlnx/cinetic
40
15
8
422
17,015
gao2025 ksana retweeted
🗿 变态开源项目 Spirula Studio,一段视频丢进去,出来就是一个能直接用的 3D 模型。 它把整条流水线塞进了单个可执行程序,不用装 Python 和 PyTorch,也不用单独装 COLMAP,NVIDIA、AMD、Intel 和苹果的显卡都能跑,界面还带简体、繁体中文在内的十几种语言。 做过三维高斯泼溅的都懂那个痛苦:先 COLMAP 算相机位姿,再配一套能跑通的 Python 环境,显卡还挑 N 卡,鱼眼和 360 素材得先去畸变才敢喂进去。Spirula Studio 用 Vulkan 来算,鱼眼、360、等距柱状投影原生支持,官方说 8GB 显存能训到一千万个 SH3 高斯点,跑完还能接着生成带贴图的网格。 迭代也凶,9 月以来基本一周一个版本,这个月刚加了从视频和照片的元数据里恢复真实尺度和方向的能力。 把三维重建从「先配三小时环境」拉回到「点开就能跑」。 GitHub:github.com/harry7557558/spir…
3
89
591
29,383
gao2025 ksana retweeted
折腾 Muse AI 注册的朋友,可以试试这个方法👇 不用开 Gemini Pro,也不用先买云电脑会员。准备一个邮箱,注册 AgentGo(免费),就可以跟着视频开始操作。 我换了几个浏览器环境,目前自己测下来,AgentGo 的通过率最高,所以把全过程录了下来,给还没注册成功的朋友参考。 先准备这几样: • 一个全新的 Gmail 或 Outlook 邮箱,能正常收验证码 • 一个 AgentGo 账号:agentgo.live/ • 如果 Muse 要求验证年龄,按页面提示完成;走银行卡验证的话,提前准备本人 Visa / Mastercard 流程很简单: 1️⃣ 注册并登录 AgentGo 2️⃣ 进入 Playground,直接选择「muse.ai」那个选项 3️⃣ 跟着演示进入注册流程,填邮箱、收验证码 4️⃣ 遇到验证环节,自己接管远程浏览器,手动完成 时区、语言、指纹这些先别急着折腾,跟着视频里的默认流程走一遍就好。 这是我目前测试下来比较顺的一条路,不敢说人人必过。卡住的话,评论区说一下具体停在哪一步,方便一起排查。 #Muse #AIAgents
193
24
13
94
53,522
gao2025 ksana retweeted
Access 1200+ design prompts jiro.build The prompt # Auren Header A cinematic, scroll-scrubbed 3D hero header for the luxury/fantasy brand "AUREN" where a full-screen background video plays frame-by-frame as the user scrolls through a 500vh section, with sequential timed overlays (title, description, feature cards, final title) revealing themselves at specific video timestamps. ## Tech stack - React 18+ with "use client" directive (Next.js App Router compatible) - framer-motion (all overlay entrance/exit animations, AnimatePresence, staggered per-character reveals) - gsap + gsap/ScrollTrigger (scroll-driven scrubbing that maps scroll progress to video.currentTime) - No icon library used; the arrow is a literal → character and the card overlay button is a literal + character ## Fonts & global styles - Import via: `fonts.googleapis.com/css2?fa…` - Display / serif font: 'Italiana', serif — used for the AUREN logo, hero titles, card numbers, and card titles. - Body / sans font: 'Inter Tight', sans-serif — weights 400 and 500 — used for nav text, descriptions, menu items, card subtitles/descriptions/buttons. - box-sizing: border-box applied to the whole section and all descendants. - Scope all styles to the section; do NOT set global body/html rules. ## Section container - Root: `.auren-header-section` — position: relative; width: 100%; height: 500vh; background: #FEFFFE. The 500vh height is what creates the scroll runway for scrubbing. - Inner sticky wrapper: `.auren-sticky-content` — position: sticky; top: 0; width: 100%; height: 100vh; overflow: hidden. Everything visible lives inside this sticky viewport. ## Structure, section by section 1. **Background video** `.auren-video-bg`: position absolute; inset 0; width/height 100%; object-fit: cover; object-position: center; z-index: 1. Element is `
1
1
4
903
gao2025 ksana retweeted
We've curated a library of 200+ carousels, made by the best design engineers & ui libraries across the internet Copy the prompt, paste it into your AI agent, and the carousel appears in your site Or give your agent access to the library via MCP, and it builds carousels like a design engineer would Ask your agent for: > "a coverflow carousel for my product screenshots" > "an infinite logo loop under the hero" > "a testimonial slider that autoplays" Carousels make a site look 10X polished, but they're a pain to build So most sites skip them, and without design taste, an AI agent ships the most generic ugly carousels on your site Access the library below 👇
2
2
12
1,742
gao2025 ksana retweeted
Opus 5.5 is absolutely cracked at motion design this entire video is code 0 After Effects 0 manual animation I showed it one viral motion post and said: “explain MakerMap, but make it insane” it came back with 20 seconds of one shape morphing through the entire product: sign up → your pin → 3,393 real makers lighting up the globe → matches → a meetup → search the crazy part? the entire animation is deterministic math the springs, cursor, morphs and motion blur are all generated inside one HTML file here’s the prompt structure steal it ↓ Ask me for: • my product + URL • 8–12 UI states that tell its story • the real data shown in each state • brand colors + fonts + accent color • required formats (1:1, 16:9, 9:16) One HTML file. One canvas One draw(t) function No CSS transitions No timers No state carried between frames One shape, never cut Every state is the same element changing size, radius and color while the content swaps A cursor drives the sequence with real clicks, typing and one drag Real UI. Real data. No placeholders. 120 BPM grid Something happens on every bea logo → button → handle field → “is this you?” → loader → pin → globe filling with users → matches → tabs → RSVP → search → logo Closed-form springs everywhere with only a tiny overshoot. If a value changes target multiple times, sum one spring per change Content enters after its container starts morphing and leaves before the next morph so text never overlaps Use a short blur on transitions Never fade black directly into the accent color. Move an accent element between states instead Make tab indicators stretch by putting each edge on a different spring Zoom the camera so every state fills the frame Make the last frame equal the first so the whole thing loops First render one frame per beat as a contact sheet Fix anything cramped or broken Then render every frame in headless Chrome at 60fps, averaging 6 subframes for motion blur Pipe into ffmpeg: H.264 + yuv420p Export all aspect ratios in parallel motion design is becoming a prompt
9
15
2
227
16,985
gao2025 ksana retweeted
everyone's sharing motion graphic videos that Opus 5.5 made, and it's genuinely insane everyone says they created it with "one prompt", but my one prompt video looked mid so i went through a bunch of these videos to see how they were actually made, and found the workflow that works here's how to generate pro level motion graphic videos w/ opus: 1. get reference videos to direct from -> whatships.com pick 1-2 videos whose style you want and tell opus to match them. naming a style works way better than describing one without a reference, opus falls back to its default look: centered text, gradient background, everything fading in that's why so many of these videos look the same. a reference gives it the pacing, the type and the transitions to copy 2. install @HyperFrames_ or @Remotion so opus can build the video both let opus write every scene as code and render it straight to mp4. no video editor without one, opus can only describe a video or hand you a rough html page you have to screen record with it, every frame is exact, and when you ask for a change it edits one line and re-renders instead of starting over 3. install @21st_dev for high quality components in the video real buttons, cards and UI components made by design engineers, instead of whatever opus invents on the spot without it, opus draws your product UI from scratch and it looks off. wrong spacing, placeholder boxes, fake-looking buttons anyone who's used good software can feel it in a second, and the whole video reads as cheap 4. steps 1-3 were context + setup. now dump all of it into opus your brand (logo, colors, fonts), screenshots of your real product, the reference video, and a quick braindump of how you see the video then ask for 3 storyboard variants without this, opus guesses your colors, your font and what your product even does. the video could be for any startup with it, it could only be yours. and 3 variants means you pick a direction instead of fixing the first idea it had 5. pick the storyboard you like ask for one still frame per scene before anything moves. fixing a storyboard is way cheaper than fixing a render without this step, you only find out scene 4 is wrong after the whole thing is animated, and every fix means re-rendering. a still frame takes seconds to change 6. let claude cook then give notes like a director: "slow every zoom to 0.7x", "hard cut here", "push in on the button" without notes, the first render is usually 80% there, and that last 20% is what makes it look pro. vague notes like "make it better" get random changes. camera words get exactly the change you want everyone has the same model. the context you give it is what makes it look pro let it cooookk
144
553
63
6,810
623,595
gao2025 ksana retweeted
steal my full workflow to create ultra-realistic AI videos with GPT-6 Astra... higgsfield just released their API, so i took it into real conditions i generated a vlog-style video set in Paris... it looks like raw footage a friend shot on a phone here's the workflow, step by step: > step 1: steal the structure, not the pixels i captured 3-5 scenes from a hotels and river views, then pulled character inspiration from pinterest and real vlogs > step 2: analyze the reference with Gemini i sent Gemini everything i'd collected... videos, audio, keyframes and it gave me a shot-by-shot breakdown, i turned that into instructions > step 3: swap the world, keep the bones i changed a lot on the character and the environment until it felt like something of my own, not a copy > step 4: build reference images first, this is where you iterate images are cheap, video is expensive so i built a character sheet, one image per location in the same mood, then the exact start frame the video opens on, all Nano Banana Pro > step 5: one 30-second video run, not ten 3-second clips the full timestamped script goes to Seedance 2.5 through the API as ONE generation start frame as the anchor, one action per beat, camera and audio described concretely, identity locks at the end so her face, outfit and makeup is locked in Seedance handles the cuts internally > step 6: revise like a director, not a gambler the first cut came back good but not right instead of re-rolling the whole 30 seconds i regenerated only the scenes that needed changes as short clips from their own start frames, then cut them into the master with ffmpeg change one variable at a time, never re-roll what already works > step 7: finish like normal footage i assembled the final cut with ffmpeg from the best takes, added ambient music from a free library and done the rules that made it work: - the reference's structure is the asset, prompt archaeology beats prompt writing - iterate on images, commit on video, the start frame decides 80% of the shot - one action per timestamped beat, crowded beats get skipped or invented - lock identity explicitly or it drifts between cuts - fix failed shots by changing one variable, redo scenes, never the whole video - the last 10% is boring editing: trim, splice, music, encode (save this workflow)
🤝 Paid partnership
26
38
2
435
27,954
gao2025 ksana retweeted
Card designs we did recently. The Dither+glitch+tracking vector combo looks great, doesn't it?
32
29
2
707
37,852
Here are the 30 absolute best FREE component libraries, design resources, and master prompts you need to save right now 🧵👇 1. Scrolltide (scrolltide.co): The ultimate vibe coding vault. 600+ master prompts for 3D, animated, and scrollytelling web templates. Paste into your AI and launch. 2. Aceternity UI (ui.aceternity.com): 200+ bold, animated React/Tailwind components for showpiece hero sections. 3. Magic UI (magicui.design): Drop-in animated React components engineered for high-converting marketing sites. 4. Motion Primitives (motion-primitives.com): Reusable React components for building advanced UI interactions. 5. OpenMotion (openmotion.design): Create and edit product demos and animations with AI. 6. Kinetics (kinetics.colorion.co): 150+ motion effects with React code and ready-to-use prompts. 7. 21st.dev (21st.dev): The NPM for vibe coding. A massive component registry that plugs directly into AI agents via MCP. 8. DESIGNmd (designmd.ai): Hundreds of design systems converted into markdown files for your AI agent. 9. VibePrompt (vibeprompts.dev): Ready-made visual prompts for dashboards, landing pages, and complex UI. 10. Refero Styles (styles.refero.design): 2,000+ real product styles with typography and ready-to-use DESIGNmd. 11. Kage (kage.design): Real UI inspiration mapped directly to prompts. 12. shadcn/ui (ui.shadcn.com): The absolute gold standard for copy-paste React/Tailwind architecture. 13. Uiverse (uiverse.io): Thousands of open-source UI elements in HTML/CSS, Tailwind, and React. 14. UIAble (uiable.com): Open-source library of React components expanding on the shadcn ecosystem. 15. mapcn (mapcn.dev): Copy-paste map components for React (markers, routes, pop-ups). 16. Component Gallery (component.gallery): 2,600+ examples of how top design systems handle the exact same UI element. 17. Minimal Gallery (minimal.gallery): Curated, high-end modern websites to feed your coding agent. 18. AppShot Gallery (appshot.gallery): Real app screenshots for mobile UI inspiration. 19. Navbar Gallery (navbar.gallery): Hundreds of high-end navigation bars. 20. Footer Design (footer.design): A dedicated gallery for well-architected footers. 21. CTA Gallery (cta.gallery): Conversion-optimized forms, pop-ups, and buttons. 22. 404s (404s.design): Creative 404 pages to copy. 23. Liquid Glass (glass.samasante.com): Generate React components with dynamic glass refraction. 24. MicroKit UI (microkit.co): Premium micro-interactions for buttons and inputs. 25. CSS Text Effects (text-effects.colorion.co): Animated text effects ready to copy. 26. Circle Loaders (circleloaders.dominikakissi.…): 24 modern SVG circular loaders. 27. Gradient Buttons (gradientbuttons.colorion.co): 1-click copyable CSS gradient buttons. 28. Kitbitz (kitbitz.art): 2,000+ free hand-drawn illustrations. 29. 3Dicons (3dicons.co): Open-source 3D icons for spatial UI. 30. Anime.js (animejs.com): A lightweight JavaScript library for complex DOM animations. What are your go-to vibe coding tools right now? Drop them below! 👇
9
71
4
450
27,641
gao2025 ksana retweeted
Some of these look too good to be true, save these👇 modulify.ai Build websites with AI with templates landdding.com — 170+ visual techniques motionin.design — Motion & interaction inspiration wonderlist.design — 127+ Figma designs
21
1
139
6,636
gao2025 ksana retweeted
2026年 最新料金 GPT-Image 2.5 — $0.0225 / 画像 GPT-Image 2 — $0.015 / 画像 Nano Banana 2 — $0.025 / 画像 待ち時間なし・生成失敗は課金なし エンタープライズ級の同時実行 ToAPIsをお試しください。

1
2
15
37,047
gao2025 ksana retweeted
jev is INSANE. in 40 seconds it broke down 724 live ads from 37 brands. every hook. every format. offer. cta. awareness stage. landing page mismatch. used 9 cents of tokens. (will be avail in @stealads + mcp)
192
459
87
6,840
1,092,889
これはやばい。。。 最近AI自動収益化が話題になってて 興味はあったんだけど勝手に自分には縁がないものだと思ってた。。 でもこの2時間の無料セミナー受けてみたら ど素人の私でもまさかの自動収益化に成功ww もし興味あればこのセミナー受けてみて👇 l.shift-ai.co.jp/lp/lpsbm11a…
31
31
6
810
490,509
gao2025 ksana retweeted
Built something new: Voice effect. Animated voice glow effect, no shades & zero dep, 3 types, multiple states, dark & light theme. libraries.dev/voice
92
123
11
2,625
112,281