wechat:Dongnan9606 Myshell Agent designer

Joined September 2019
我开源了一个性价比极高的数字人skills,可以帮助你随意的制作口播视频。只需要你提供文案,口播静态图和你的音频即可。下面是这个skills制作的视频。
3
1
194
30秒视频价格不到1块
28
开源一个口播一条龙skills,从配音,视频,动画,全部交给AI完成。你只需要提供口播图片、文案、自己的20秒的音色即可。项目地址在下方 bilibili.com/video/BV1Z1HD6F…
1
125
I trained an open-source LoRA for MiniMax H3: Realism People. weights are open. and the exact trainer I used is now available to everyone on @fal Lora Link : huggingface.co/fal/MiniMax-H… Trainer : fal.ai/models/minimax/h3/ref…
LoRA trainer for MiniMax H3 is now available on fal. to show what it can do, we trained Realism People, an open-source LoRA that pushes H3 toward raw, photorealistic humans. skin, eyes, motion. More LoRA coming soon !
37
61
8
801
67,185
最近做了一个概念场景生成的krea2 LORA,可以方便的生成很不错的场景,用于AI短剧的制作,目前上线runninghub,欢迎调用。模型搜索-Krea2真实美学-OLDX 即可使用。 工作流地址:runninghub.cn/post/207512661…
2
1,039
最近使用seedance2.0做的一段高燃打斗特效
1
2
363
𝐓𝐇𝐄 𝐕𝐈𝐊𝐈𝐍𝐆 🆚 T𝐇𝐄 𝐆𝐄𝐍𝐄𝐑𝐀𝐋 AI Fan Film May the best win
27
76
7
1,414
374,319
AiOLDX retweeted
姚老师又开始掏箱底了,哈哈哈。
开源一个教程Skill 打磨了十几版,效果还不错,已推到GitHub 如果想在五一假期高质量充电,或随时给自己生成一份定制高质量教程 欢迎下载 基本逻辑: 1、输入任意主题及参考资料,AI会优先以参考资料为核心,然后根据需要进行高质量素材和资料补充,这个过程中融入了低质量信源的过滤机制 2、AI会结合教程的特点,并结合用户的部分偏好,生成定制深度教程,输出PDF、Word及HTML三种格式,方便自己学习 3、教程内容,按照章节的逻辑进行系统性的输出,同时根据各章节内容特点,自行画图并插入到章节相关内容模块中 4、教程融入了三年前经营MCN时写的《课程营销学》的相关底层逻辑与方法,回头也把这本书给开源出来 5、排版与UI,输出的文档与教程网页,有结合 @HiTw93 的kami进行借鉴和融入,实现了很有质感的排版规范 示例报告有3个,其中一个示例教程示例来自 @ReyJudgementOS 的一篇英语干货文章:《12岁英语自由:我“带”孩子“学”英语的经验与教训》 教程Skill的GitHub地址: github.com/yaojingang/yao-op…
25
32
1
181
58,596
分享一个特别牛逼的 Skill ,叫:Markdown Viewer Skill 。 这个 Skill 里包含了一百多个图例,6000 多精选矢量图标,一句话就可以根据你的 Markdown 内容自动定制各种图表和配图。 使用方式就是:把你的 MarkDown 文件让给 Claude Code 这类工具,然后说:充分了解这个 Skills ,然后给我的这份文档生成配图或者图表。 然后,就会自动生成各类的图表,比如:流程图、架构图等,最牛的是可以自动插入到你的 MarkDown 文件里。 安装方式: npx skills add markdown-viewer/skills 传送门地址:github.com/markdown-viewer/s…
7
266
8
1,518
120,836
1/10 🚀 Qwen3.5-Omni is here! Scaling up to a native omni-modal AGI. Meet the next generation of Qwen, designed for native text, image, audio, and video understanding, with major advances in both intelligence and real-time interaction. A standout feature: Audio-Visual Vibe Coding: Describe your vision to the camera, and Qwen3.5-Omni instantly builds a functional website or game for you. Highlights: Script-Level Captioning: Generate detailed video scripts with timestamps, scene cuts & speaker mapping. SOTA Performance: Qwen3.5-Omni has secured 215 SOTA scores across various sub-tasks, matching the top-tier text/vision capabilities of the Qwen3.5 series. Audio-Visual Understanding: From auto-segmentation to fine-grained script generation, it understands the relationship between characters and their environment like never before. Seamless Interaction: With native API support for Semantic Interruption, voice conversations feel human-like and background-noise resistant. Global Multilingual Mastery: Pioneering support for 74 languages in speech recognition and 29 languages in expressive speech generation, breaking down global communication barriers. Autonomous Intelligence: Native support for WebSearch and complex Function Calling—the model now independently decides when to pull real-time data. Qwen3.5-Omni is built to be the backbone of next-gen AI applications, empowering developers and users alike with true multimodal reasoning.
73
267
52
2,192
11,373,834
I recorded a 25-min tutorial on prompting $50,000 landing pages with Gemini + Nano Banana
27
130
5
1,136
79,594
Luma 发布了一个很厉害的图片模型 UN1 类似 Nano Banana 和 Midjourney 的集合体 支持常识场景补全、空间关系理解和合理的画面变化; 支持多图参考、风格迁移; 支持各种文化、审美、风格的图像生成和理解,尤其是对当代视觉文化和梗图的生成; 最重要的看起来支持中文;
Uni-1 is here! A new kind of model that thinks and generates pixels simultaneously. Less artificial. More intelligent.
11
18
2
148
35,887
Access ALL prompts for stunning animated websites in one click: motionsites.ai 🎯 FULL RECREATION PROMPT Build a single-page landing page for an AI-powered web design agency using React + Vite + TypeScript + Tailwind CSS + shadcn/ui. The aesthetic is dark, premium, Apple-inspired with a custom "liquid glass" morphism effect. Pure black background throughout. FONTS & DESIGN SYSTEM Google Fonts import: Instrument Serif (italic) — headings Barlow (300, 400, 500, 600) — body text Tailwind config — extend fontFamily: heading: ["'Instrument Serif'", "serif"] body: ["'Barlow'", "sans-serif"] CSS Variables (:root in index.css): --background: 213 45% 67%; --foreground: 0 0% 100%; --primary: 0 0% 100%; --primary-foreground: 213 45% 67%; --border: 0 0% 100% / 0.2; --radius: 9999px; --font-heading: 'Instrument Serif', serif; --font-body: 'Barlow', sans-serif; All headings use: font-heading italic text-white tracking-tight leading-[0.9] All body text uses: font-body font-light text-white/60 text-sm All buttons use: font-body with rounded-full LIQUID GLASS CSS (in @layer components) Two variants — .liquid-glass (subtle) and .liquid-glass-strong (more visible): .liquid-glass: background: rgba(255, 255, 255, 0.01); background-blend-mode: luminosity; backdrop-filter: blur(4px); border: none; box-shadow: inset 0 1px 1px rgba(255, 255, 255, 0.1); position: relative; overflow: hidden; ::before pseudo-element — a gradient border mask: content: ''; position: absolute; inset: 0; border-radius: inherit; padding: 1.4px; background: linear-gradient(180deg, rgba(255,255,255,0.45) 0%, rgba(255,255,255,0.15) 20%, rgba(255,255,255,0) 40%, rgba(255,255,255,0) 60%, rgba(255,255,255,0.15) 80%, rgba(255,255,255,0.45) 100%); -webkit-mask: linear-gradient(#fff 0 0) content-box, linear-gradient(#fff 0 0); -webkit-mask-composite: xor; mask-composite: exclude; pointer-events: none; .liquid-glass-strong: Same but backdrop-filter: blur(50px), stronger box-shadow: 4px 4px 4px rgba(0,0,0,0.05), inset 0 1px 1px rgba(255,255,255,0.15), and slightly higher gradient opacity (0.5 / 0.2). SECTION 1 — NAVBAR (fixed) Fixed at top-4, full-width, z-50. Left: logo image (48×48). Center: a liquid-glass rounded-full pill containing nav links ("Home", "Services", "Work", "Process", "Pricing") as text-sm font-medium text-foreground/90 + a solid white bg-white text-black rounded-full "Get Started" button with ArrowUpRight icon. SECTION 2 — HERO (1000px height) Container: relative overflow-visible, height 1000px, black background. Background video: src: d8j0ntlcm91z4.cloudfront.net… Position: absolute, top: 20%, w-full h-auto object-contain z-0 Autoplay, loop, muted, playsInline Poster fallback image at /images/hero_bg.jpeg Overlays: absolute inset-0 bg-black/5 z-0 (light darkening) Bottom gradient: absolute bottom-0 left-0 right-0 z-[1], height 300px, linear-gradient(to bottom, transparent, black) Content (z-10, centered, paddingTop 150px): Badge pill: liquid-glass rounded-full containing a white bg-white text-black rounded-full "New" tag + "Introducing AI‑powered web design." text Heading: Use a BlurText animation component — text: "The Website Your Brand Deserves" — text-6xl md:text-7xl lg:text-[5.5rem] font-heading italic text-foreground leading-[0.8] tracking-[-4px] — animates word-by-word from bottom with blur-to-clear effect (delay 100ms per word) Subtext (motion.p): "Stunning design. Blazing performance. Built by AI, refined by experts. This is web design, wildly reimagined." — fades in with blur at 0.8s delay CTA buttons (motion.div, 1.1s delay): liquid-glass-strong rounded-full "Get Started" + ArrowUpRight icon, and a text-only "Watch the Film" + Play icon Partners bar at bottom (mt-auto pb-8 pt-16) BlurText component: Uses motion/react (framer-motion). Splits text by words, each word animates via IntersectionObserver with filter: blur(10px) → blur(5px) → blur(0px), opacity: 0 → 0.5 → 1, y: 50 → -5 → 0. Step duration 0.35s. SECTION 3 — PARTNERS BAR Centered column. Top: liquid-glass rounded-full badge "Trusted by the teams behind". Below: horizontal row of partner names ("Stripe", "Vercel", "Linear", "Notion", "Figma") rendered as text-2xl md:text-3xl font-heading italic text-white, gap-12. SECTION 4 — START SECTION ("How It Works") Full-width section, min-height: 700px, py-32 px-6 md:px-16 lg:px-24. Background HLS video: src: stream.mux.com/9JXDljEVWYwWu… Use hls.js library. Absolute, full cover, z-0. Top + bottom fade gradients (200px each, black ↔ transparent). Content (z-10, centered, min-height 500px): Badge: liquid-glass rounded-full — "How It Works" Heading: "You dream it. We ship it." — text-4xl md:text-5xl lg:text-6xl font-heading italic Subtext: "Share your vision. Our AI handles the rest—wireframes, design, code, launch. All in days, not quarters." Button: liquid-glass-strong rounded-full "Get Started" + ArrowUpRight SECTION 5 — FEATURES CHESS (alternating rows) py-24 px-6 md:px-16 lg:px-24. Header: badge "Capabilities", heading "Pro features. Zero complexity." Row 1 (text left, image right): H3: "Designed to convert. Built to perform." P: "Every pixel is intentional. Our AI studies what works across thousands of top sites—then builds yours to outperform them all." Button: liquid-glass-strong rounded-full "Learn more" Image: GIF in liquid-glass rounded-2xl overflow-hidden container Row 2 (image left, text right — using lg:flex-row-reverse): H3: "It gets smarter. Automatically." P: "Your site evolves on its own. AI monitors every click, scroll, and conversion—then optimizes in real time. No manual updates. Ever." Button: "See how it works" SECTION 6 — FEATURES GRID (4 columns) Badge "Why Us", heading "The difference is everything." 4 cards in grid-cols-1 md:grid-cols-2 lg:grid-cols-4 gap-6. Each card: liquid-glass rounded-2xl p-6. Contains: Icon in liquid-glass-strong rounded-full w-10 h-10 circle Title: text-lg font-heading italic text-white Description: text-white/60 font-body font-light text-sm Cards: ⚡ Zap — "Days, Not Months" — "Concept to launch at a pace that redefines fast." 🎨 Palette — "Obsessively Crafted" — "Every detail considered. Every element refined." 📊 BarChart3 — "Built to Convert" — "Layouts informed by data. Decisions backed by performance." 🛡️ Shield — "Secure by Default" — "Enterprise-grade protection comes standard." SECTION 7 — STATS Background HLS video: src: stream.mux.com/NcU3HlHeF7CUL… Desaturated: style={{ filter: 'saturate(0)' }}. Top + bottom black fades (200px). Content (z-10): liquid-glass rounded-3xl p-12 md:p-16, grid grid-cols-2 lg:grid-cols-4 gap-8 text-center: "200+" — "Sites launched" "98%" — "Client satisfaction" "3.2x" — "More conversions" "5 days" — "Average delivery" Values: text-4xl md:text-5xl lg:text-6xl font-heading italic text-white Labels: text-white/60 font-body font-light text-sm SECTION 8 — TESTIMONIALS Badge "What They Say", heading "Don't take our word for it." 3-column grid. Each: liquid-glass rounded-2xl p-8. Quote in text-white/80 font-body font-light text-sm italic. Name: text-white font-body font-medium text-sm. Role: text-white/50 font-body font-light text-xs. Testimonials: Sarah Chen, CEO Luminary — "A complete rebuild in five days..." Marcus Webb, Head of Growth Arcline — "Conversions up 4x..." Elena Voss, Brand Director Helix — "They didn't just design our site..." SECTION 9 — CTA FOOTER Background HLS video: src: stream.mux.com/8wrHPCX2dC3ms… Top + bottom black fades (200px). Content (z-10, centered): Heading: "Your next website starts here." — text-5xl md:text-6xl lg:text-7xl Subtext: "Book a free strategy call. See what AI‑powered design can do." Two buttons: liquid-glass-strong "Book a Call" + solid bg-white text-black "View Pricing" Footer: mt-32 pt-8 border-t border-white/10, copyright "© 2026 Studio" + links (Privacy, Terms, Contact) in text-white/40 text-xs DEPENDENCIES hls.js, motion (framer-motion), lucide-react, tailwindcss-animate KEY PATTERNS All section badges use: liquid-glass rounded-full px-3.5 py-1 text-xs font-medium text-white font-body inline-block mb-4 All section headings use: text-4xl md:text-5xl lg:text-6xl font-heading italic text-white tracking-tight leading-[0.9] All video sections use HLS via hls.js with Safari fallback (canPlayType) All video fades: 200px height, linear-gradient(to bottom/top, black, transparent) Outer page wrapper: bg-black overflow-visible Here's the complete, detailed prompt to recreate this landing page: PROMPT TO RECREATE LANDING PAGE Build a single-page landing page for an AI-powered web design agency using React + Vite + TypeScript + Tailwind CSS + shadcn/ui. The aesthetic is dark, premium, Apple-inspired with a custom "liquid glass" morphism effect. Pure black background throughout. FONTS & DESIGN SYSTEM Google Fonts import: Instrument Serif (italic) — headings Barlow (300, 400, 500, 600) — body text Tailwind config — extend fontFamily: heading: ["'Instrument Serif'", "serif"] body: ["'Barlow'", "sans-serif"] CSS Variables (:root in index.css): --background: 213 45% 67%; --foreground: 0 0% 100%; --primary: 0 0% 100%; --primary-foreground: 213 45% 67%; --border: 0 0% 100% / 0.2; --radius: 9999px; --font-heading: 'Instrument Serif', serif; --font-body: 'Barlow', sans-serif; All headings use: font-heading italic text-white tracking-tight leading-[0.9] All body text uses: font-body font-light text-white/60 text-sm All buttons use: font-body with rounded-full LIQUID GLASS CSS (in @layer components) Two variants — .liquid-glass (subtle) and .liquid-glass-strong (more visible): .liquid-glass: background: rgba(255, 255, 255, 0.01); background-blend-mode: luminosity; backdrop-filter: blur(4px); border: none; box-shadow: inset 0 1px 1px rgba(255, 255, 255, 0.1); position: relative; overflow: hidden; ::before pseudo-element — a gradient border mask: content: ''; position: absolute; inset: 0; border-radius: inherit; padding: 1.4px; background: linear-gradient(180deg, rgba(255,255,255,0.45) 0%, rgba(255,255,255,0.15) 20%, rgba(255,255,255,0) 40%, rgba(255,255,255,0) 60%, rgba(255,255,255,0.15) 80%, rgba(255,255,255,0.45) 100%); -webkit-mask: linear-gradient(#fff 0 0) content-box, linear-gradient(#fff 0 0); -webkit-mask-composite: xor; mask-composite: exclude; pointer-events: none; .liquid-glass-strong: Same but backdrop-filter: blur(50px), stronger box-shadow: 4px 4px 4px rgba(0,0,0,0.05), inset 0 1px 1px rgba(255,255,255,0.15), and slightly higher gradient opacity (0.5 / 0.2). SECTION 1 — NAVBAR (fixed) Fixed at top-4, full-width, z-50. Left: logo image (48×48). Center: a liquid-glass rounded-full pill containing nav links ("Home", "Services", "Work", "Process", "Pricing") as text-sm font-medium text-foreground/90 + a solid white bg-white text-black rounded-full "Get Started" button with ArrowUpRight icon. SECTION 2 — HERO (1000px height) Container: relative overflow-visible, height 1000px, black background. Background video: src: d8j0ntlcm91z4.cloudfront.net… Position: absolute, top: 20%, w-full h-auto object-contain z-0 Autoplay, loop, muted, playsInline Poster fallback image at /images/hero_bg.jpeg Overlays: absolute inset-0 bg-black/5 z-0 (light darkening) Bottom gradient: absolute bottom-0 left-0 right-0 z-[1], height 300px, linear-gradient(to bottom, transparent, black) Content (z-10, centered, paddingTop 150px): Badge pill: liquid-glass rounded-full containing a white bg-white text-black rounded-full "New" tag + "Introducing AI‑powered web design." text Heading: Use a BlurText animation component — text: "The Website Your Brand Deserves" — text-6xl md:text-7xl lg:text-[5.5rem] font-heading italic text-foreground leading-[0.8] tracking-[-4px] — animates word-by-word from bottom with blur-to-clear effect (delay 100ms per word) Subtext (motion.p): "Stunning design. Blazing performance. Built by AI, refined by experts. This is web design, wildly reimagined." — fades in with blur at 0.8s delay CTA buttons (motion.div, 1.1s delay): liquid-glass-strong rounded-full "Get Started" + ArrowUpRight icon, and a text-only "Watch the Film" + Play icon Partners bar at bottom (mt-auto pb-8 pt-16) BlurText component: Uses motion/react (framer-motion). Splits text by words, each word animates via IntersectionObserver with filter: blur(10px) → blur(5px) → blur(0px), opacity: 0 → 0.5 → 1, y: 50 → -5 → 0. Step duration 0.35s. SECTION 3 — PARTNERS BAR Centered column. Top: liquid-glass rounded-full badge "Trusted by the teams behind". Below: horizontal row of partner names ("Stripe", "Vercel", "Linear", "Notion", "Figma") rendered as text-2xl md:text-3xl font-heading italic text-white, gap-12. SECTION 4 — START SECTION ("How It Works") Full-width section, min-height: 700px, py-32 px-6 md:px-16 lg:px-24. Background HLS video: src: stream.mux.com/9JXDljEVWYwWu… Use hls.js library. Absolute, full cover, z-0. Top + bottom fade gradients (200px each, black ↔ transparent). Content (z-10, centered, min-height 500px): Badge: liquid-glass rounded-full — "How It Works" Heading: "You dream it. We ship it." — text-4xl md:text-5xl lg:text-6xl font-heading italic Subtext: "Share your vision. Our AI handles the rest—wireframes, design, code, launch. All in days, not quarters." Button: liquid-glass-strong rounded-full "Get Started" + ArrowUpRight SECTION 5 — FEATURES CHESS (alternating rows) py-24 px-6 md:px-16 lg:px-24. Header: badge "Capabilities", heading "Pro features. Zero complexity." Row 1 (text left, image right): H3: "Designed to convert. Built to perform." P: "Every pixel is intentional. Our AI studies what works across thousands of top sites—then builds yours to outperform them all." Button: liquid-glass-strong rounded-full "Learn more" Image: GIF in liquid-glass rounded-2xl overflow-hidden container Row 2 (image left, text right — using lg:flex-row-reverse): H3: "It gets smarter. Automatically." P: "Your site evolves on its own. AI monitors every click, scroll, and conversion—then optimizes in real time. No manual updates. Ever." Button: "See how it works" SECTION 6 — FEATURES GRID (4 columns) Badge "Why Us", heading "The difference is everything." 4 cards in grid-cols-1 md:grid-cols-2 lg:grid-cols-4 gap-6. Each card: liquid-glass rounded-2xl p-6. Contains: Icon in liquid-glass-strong rounded-full w-10 h-10 circle Title: text-lg font-heading italic text-white Description: text-white/60 font-body font-light text-sm Cards: ⚡ Zap — "Days, Not Months" — "Concept to launch at a pace that redefines fast." 🎨 Palette — "Obsessively Crafted" — "Every detail considered. Every element refined." 📊 BarChart3 — "Built to Convert" — "Layouts informed by data. Decisions backed by performance." 🛡️ Shield — "Secure by Default" — "Enterprise-grade protection comes standard." SECTION 7 — STATS Background HLS video: src: stream.mux.com/NcU3HlHeF7CUL… Desaturated: style={{ filter: 'saturate(0)' }}. Top + bottom black fades (200px). Content (z-10): liquid-glass rounded-3xl p-12 md:p-16, grid grid-cols-2 lg:grid-cols-4 gap-8 text-center: "200+" — "Sites launched" "98%" — "Client satisfaction" "3.2x" — "More conversions" "5 days" — "Average delivery" Values: text-4xl md:text-5xl lg:text-6xl font-heading italic text-white Labels: text-white/60 font-body font-light text-sm SECTION 8 — TESTIMONIALS Badge "What They Say", heading "Don't take our word for it." 3-column grid. Each: liquid-glass rounded-2xl p-8. Quote in text-white/80 font-body font-light text-sm italic. Name: text-white font-body font-medium text-sm. Role: text-white/50 font-body font-light text-xs. Testimonials: Sarah Chen, CEO Luminary — "A complete rebuild in five days..." Marcus Webb, Head of Growth Arcline — "Conversions up 4x..." Elena Voss, Brand Director Helix — "They didn't just design our site..." SECTION 9 — CTA FOOTER Background HLS video: src: stream.mux.com/8wrHPCX2dC3ms… Top + bottom black fades (200px). Content (z-10, centered): Heading: "Your next website starts here." — text-5xl md:text-6xl lg:text-7xl Subtext: "Book a free strategy call. See what AI‑powered design can do." Two buttons: liquid-glass-strong "Book a Call" + solid bg-white text-black "View Pricing" Footer: mt-32 pt-8 border-t border-white/10, copyright "© 2026 Studio" + links (Privacy, Terms, Contact) in text-white/40 text-xs DEPENDENCIES hls.js, motion (framer-motion), lucide-react, tailwindcss-animate KEY PATTERNS All section badges use: liquid-glass rounded-full px-3.5 py-1 text-xs font-medium text-white font-body inline-block mb-4 All section headings use: text-4xl md:text-5xl lg:text-6xl font-heading italic text-white tracking-tight leading-[0.9] All video sections use HLS via hls.js with Safari fallback (canPlayType) All video fades: 200px height, linear-gradient(to bottom/top, black, transparent) Outer page wrapper: bg-black overflow-visible
27
142
13
1,118
114,470
LTX 2.3 is so good at lipsync out of the box
4
3
1
78
25,755
Step 1: Chat GPT 5.2 instructions: - Create 20 character concept prompts on a white background - The theme must be [describe your main theme] - The secondary instructions are [Secondary instruction] - The prompt must follow this structure {prompt1, prompt2, prompt3, ..., prompt20} - In the prompts, replace “,” with “.”, since commas are used here to separate the prompts - After the prompt batch in {}, add --ar 3:4 --sref 3925989607 1215797590 --niji 7 Here, “--sref 3925989607 1215797590 --niji 7” is used for the tremendous visual clarity of these concept artworks, and a good balance between adherence to the prompt and exploratory capabilities. Exemple of result : {atom-punk female reactor mechanic in a reinforced flight jacket with glowing isotope canisters and heavy boots. white background. character concept art. full body. badass stance, atom-punk wasteland captain with a radium saber and chrome shoulder armor. white background. character concept art. full body. fierce expression, retro-futurist atomic biker queen with a split visor helmet under one arm and a plasma revolver holster. white background. character concept art. full body. confident pose, nuclear lab renegade woman in a fitted lead-lined jumpsuit with hazard patches and neon green tubing. white background. character concept art. full body. intense attitude, atom-punk bounty hunter with a mini reactor backpack and tesla lasso on her hip. white background. character concept art. full body. dynamic pose, postwar atomic priestess warrior with irradiated glass pauldrons and a glowing rosary device. white background. character concept art. full body. commanding presence, retro sci-fi commando woman with a uranium core gauntlet and armored corset plating. white background. character concept art. full body. sharp silhouette, atom-punk street samurai female with a cathode katana and analog scanner monocle. white background. character concept art. full body. battle ready, nuclear desert raider queen with patched leather layers and a Geiger counter belt full of tools. white background. character concept art. full body. intimidating look, atomic aviator heroine with a cropped bomber jacket radiation insignia and jet fins on boots. white background. character concept art. full body. heroic pose, radium nightclub enforcer with elegant retro armor high collar and crackling baton. white background. character concept art. full body. stylish and dangerous, atom-punk engineer duelist with articulated exosleeves and a compact coil rifle. white background. character concept art. full body. grounded stance, fallout metropolis vigilante woman with neon hazard stripes and an anti-rad shield buckler. white background. character concept art. full body. determined gaze, retro atomic diver operative with a slim pressure suit and glowing helmet ring opened back. white background. character concept art. full body. poised and lethal, atom-punk heavy gunner with reinforced thigh armor and a shoulder mounted micro reactor cannon. white background. character concept art. full body. powerful posture, nuclear courier outlaw with sealed satchels isotope tags and a hidden pulse dagger. white background. character concept art. full body. cool expression, atomic arena champion woman with chrome knee guards and a luminous chain whip. white background. character concept art. full body. aggressive stance, rad-tech hacker mercenary with vacuum tube implants and a portable signal disruptor. white background. character concept art. full body. confident smirk, atom-punk royal guard captain with polished lead armor and a ceremonial plasma halberd. white background. character concept art. full body. elite presence, retro future scavenger queen with asymmetrical armor scrap reactor gems and rugged military boots. white background. character concept art. full body. fearless pose, nuclear storm rider woman with insulated trench coat arc coils and a visor lit in toxic green. white background. character concept art. full body. cinematic concept} --ar 3:4 --sref 3925989607 1215797590 --niji 7 Step 2: Select the character you are interested in, then in Nano Banana pro (ideally on freepik), apply this simple prompt: Convert @ character into a modern cinematic 3D render with a high-fashion grade, punchy yet natural contrast, filmic color science, subtle halation/bloom, controlled highlights, realistic materials, preserve the original camera framing, no text, no logo, solid #ffffff white background
9
14
3
166
9,062
Claude Code 有个隐藏设置,装了之后代码导航速度能快几百倍。 原理是这样:默认情况下 Claude Code 用文本搜索找代码,跟你在文件夹里 Ctrl+F 一样,一个个文件翻。装了 LSP 插件之后,它用的是和 VS Code 一样的代码理解引擎——直接知道每个函数在哪定义、谁在调用、改了影响什么。 体感上的区别:你让它改一个功能,之前它会在几百个文件里乱翻,经常找错,白白烧你的对话额度。现在它直接跳到正确位置,省时间也省额度。 不想折腾的话,直接跟 Claude Code 说"帮我装 TypeScript LSP 插件",它自己会搞定。
claude code has a hidden setting that makes it 600x faster and almost nobody knows about it by default it uses text grep to find functions. it doesn't understand your code at all. that's why it takes 30-60 seconds and sometimes returns the wrong file there's a flag called ENABLE_LSP_TOOL that connects it to language servers. same tech that powers vscode's ctrl+click to jump straight to the definition after enabling it: > "add a stripe webhook to my payments page" - claude finds your existing payment logic in 50ms instead of grepping through hundreds of files > "fix the auth bug on my dashboard" - traces the actual call hierarchy instead of guessing which file handles auth > after every edit it auto-catches type errors immediately instead of you finding them 10 prompts later also saves tokens because claude stops wasting context searching for the wrong files 2 minute setup and it works for 11 languages
18
61
3
398
91,278
You are an award-winning trailer director + cinematographer + storyboard artist. Your job: turn ONE reference image into a cohesive cinematic short sequence, then output AI-video-ready keyframes. User provides: one reference image (image). 1) First, analyze the full composition: identify ALL key subjects (person/group/vehicle/object/animal/props/environment elements) and describe spatial relationships and interactions (left/right/foreground/background, facing direction, what each is doing). 2) Do NOT guess real identities, exact real-world locations, or brand ownership. Stick to visible facts. Mood/atmosphere inference is allowed, but never present it as real-world truth. 3) Strict continuity across ALL shots: same subjects, same wardrobe/appearance, same environment, same time-of-day and lighting style. Only action, expression, blocking, framing, angle, and camera movement may change. 4) Depth of field must be realistic: deeper in wides, shallower in close-ups with natural bokeh. Keep ONE consistent cinematic color grade across the entire sequence. 5) Do NOT introduce new characters/objects not present in the reference image. If you need tension/conflict, imply it off-screen (shadow, sound, reflection, occlusion, gaze). Expand the image into a 10–20 second cinematic clip with a clear theme and emotional progression (setup → build → turn → payoff). The user will generate video clips from your keyframes and stitch them into a final sequence. Output (with clear subheadings): - Subjects: list each key subject (A/B/C…), describe visible traits (wardrobe/material/form), relative positions, facing direction, action/state, and any interaction. - Environment & Lighting: interior/exterior, spatial layout, background elements, ground/walls/materials, light direction & quality (hard/soft; key/fill/rim), implied time-of-day, 3–8 vibe keywords. - Visual Anchors: list 3–6 visual traits that must stay constant across all shots (palette, signature prop, key light source, weather/fog/rain, grain/texture, background markers). From the image, propose: - Theme: one sentence. - Logline: one restrained trailer-style sentence grounded in what the image can support. - Emotional Arc: 4 beats (setup/build/turn/payoff), one line each. Choose and explain your filmmaking approach (must include): - Shot progression strategy: how you move from wide to close (or reverse) to serve the beats - Camera movement plan: push/pull/pan/dolly/track/orbit/handheld micro-shake/gimbal—and WHY - Lens & exposure suggestions: focal length range (18/24/35/50/85mm etc.), DoF tendency (shallow/medium/deep), shutter “feel” (cinematic vs documentary) - Light & color: contrast, key tones, material rendering priorities, optional grain (must match the reference style) Output a Keyframe List: default 9–12 frames (later assembled into ONE master grid). These frames must stitch into a coherent 10–20s sequence with a clear 4-beat arc. Each frame must be a plausible continuation within the SAME environment. Use this exact format per frame: [KF# | suggested duration (sec) | shot type (ELS/LS/MLS/MS/MCU/CU/ECU/Low/Worm’s-eye/High/Bird’s-eye/Insert)] - Composition: subject placement, foreground/mid/background, leading lines, gaze direction - Action/beat: what visibly happens (simple, executable) - Camera: height, angle, movement (e.g., slow 5% push-in / 1m lateral move / subtle handheld) - Lens/DoF: focal length (mm), DoF (shallow/medium/deep), focus target - Lighting & grade: keep consistent; call out highlight/shadow emphasis - Sound/atmos (optional): one line (wind, city hum, footsteps, metal creak) to support editing rhythm Hard requirements: - Must include: 1 environment-establishing wide, 1 intimate close-up, 1 extreme detail ECU, and 1 power-angle shot (low or high). - Ensure edit-motivated continuity between shots (eyeline match, action continuation, consistent screen direction / axis). You MUST additionally output ONE single master image: a Cinematic Contact Sheet / Storyboard Grid containing ALL keyframes in one large image. - Default grid: 3x3. If more than 9 keyframes, use 4x3 or 5x3 so every keyframe fits into ONE image. Requirements: 1) The single master image must include every keyframe as a separate panel (one shot per cell) for easy selection. 2) Each panel must be clearly labeled: KF number + shot type + suggested duration (labels placed in safe margins, never covering the subject). 3) Strict continuity across ALL panels: same subjects, same wardrobe/appearance, same environment, same lighting & same cinematic color grade; only action/expression/blocking/framing/movement changes. 4) DoF shifts realistically: shallow in close-ups, deeper in wides; photoreal textures and consistent grading. 5) After the master grid image, output the full text breakdown for each KF in order so the user can regenerate any single frame at higher quality. Output in this order: A) Scene Breakdown B) Theme & Story C) Cinematic Approach D) Keyframes (KF# list) E) ONE Master Contact Sheet Image (All KFs in one grid)
I didn't expect this change to attract so much attention. I did some more testing to verify its stability. Below is a test I conducted using screenshots from Harry Potter. Because the prompt was quite long, I've compiled it into an image and posted it in the comments. Thanks again to @techhalla for the great idea.
31
121
8
1,176
317,842
MyShell and @questflow share a long-term vision for the emerging agent-native ecosystem. As early builders in the x402 landscape, both teams are aligned in supporting an open, scalable agent world — one that enables new forms of interaction between creators, developers, and intelligent systems. This collaboration strengthens our shared commitment to advancing the foundations of the agent era. More ahead.
65
46
10
100
70,320