分类筛选
找到 434 个 Demo
Built a polaroid camera component in Workshop usi...
Built a polaroid camera component in @framer Workshop using Gemini 3. Customisations include → shutter sound, camera color, paper texture, text controls, etc. Prompt and Link 👇 https://t.co/y29G1ZgkL7
Gemini 3 has a capability most people don't even k...
Gemini 3 has a capability most people don't even know exists. it's not the 1M tokens. it's not the multimodal processing. it's something else entirely. And it's the reason I built 3,000+ prompts specifically for Gemini 3. Everyone talks about Gemini's specs: → 1 million token context → Native multimodal inputs → Deep Think mode → Agentic workflows But they're missing what happens when you combine these features. The secret is persistent systems thinking. Gemini 3 doesn't just process large contexts. It maintains coherent reasoning ACROSS those contexts while simultaneously: - Analyzing images - Reading documents - Planning multi-step workflows - Adapting based on previous outputs This creates emergent capabilities that don't exist in other models. I built 3,000+ prompts that exploit this. Each prompt is built around this core insight: Gemini 3's real power isn't WHAT it can process. It's HOW it connects everything together. The library includes: ✓ 3,000+ production-ready prompts ✓ Organized by difficulty (beginner → advanced) ✓ Real use cases for each prompt Like, RT + reply "GEMINI" and I'll DM you the guide. (Must be following so I can DM) Skip this and keep wondering why your Gemini results feel the same as ChatGPT. Or grab the library and start using the capability everyone's missing.
introducing: The Claw a webgame built with threej...
introducing: The Claw a webgame built with threejs, mediapipe computer vision, and gemini 3 how many alien friends can you save? https://t.co/XUDbXclaAp
We just dropped Nano Banana Pro, built on Gemini 3...
We just dropped Nano Banana Pro, built on Gemini 3. 🍌 With state-of-the-art text rendering, vast world knowledge and studio-quality creative controls, Gemini 3 Pro Image can create and edit more complex visuals, infographics and more. Here’s what’s under the hood. 🧵
Built this dither generator using . Gemini 3 Pro
Built this dither generator using .@antigravity Gemini 3 Pro https://t.co/QzUiJY0Jtg
It's crazy to see how Gemini 3 Pro dominates every...
It's crazy to see how Gemini 3 Pro dominates everything it's built for! https://t.co/a2plpo4ViG
Gemini 3.0 is absolutely insane... Built with De...
Gemini 3.0 is absolutely insane... Built with @Replit Design, link below. https://t.co/x4YnU9kvmn
This is honestly so cool. Using one of the free...
This is honestly so cool. Using one of the free @ComfyUI templates (wanvideo2_2_I2V_A14B_TimeToMove_example), you can turn a simple base animation (left video) into a fully realistic motion clip (on the right). I even built a small app with @Google Gemini 3 to generate the basic animation… and the result looks incredible. Just wow.
something that didn't get enough attention Gemini...
something that didn't get enough attention Gemini 3 wasn't trained on Nvidia chips; it ran fully on Google’s own TPUs that's not surprising, but it does show that Google built a fully independent stack and rolled it out across its own products that gives Google a real moat in this race.
I jumped on Gemini 3 Pro the moment it dropped and...
I jumped on Gemini 3 Pro the moment it dropped and built a real-time 3D particle sim with Three.js that reacts to touch on my site. Particles heat up with force, cool through color, and gather under a soft center gravity inside a cube. Try it here: https://t.co/GeoMalREN4 https://t.co/MYXALVoCAN
Made a dance game for families… & drunk people...
Made a dance game for families… & drunk people 😂 Built in a single shot with Gemini 3.0. Inspo: @ann_nnng 👉https://t.co/zv6TR62w9G It’s sooo much fun to play! Try it yourself 😉☀️ https://t.co/agQLytnE9W
R.I.P. to boring Meta ad copy. Gemini 3 changed e...
R.I.P. to boring Meta ad copy. Gemini 3 changed everything for DTC brands writing Facebook ads. I've tested every AI model for Meta ad copy. Claude, GPT-4, GPT-5, custom fine-tuned tools... They're all fine. But fine doesn't stop the scroll. So I built a Meta Ad Copy Engine as a custom Gemini Gem. And trained it on hooks and frameworks from top-performing DTC campaigns. Here's what it does: → You give it your product and target audience → It generates 5 scroll-stopping hook variations → Creates full ad copy using proven frameworks (PAS, Before/After, Testimonial-style) → Outputs headlines and descriptions ready to paste into Ads Manager → Adjusts copy based on awareness level (cold, warm, hot) No more staring at a blank screen. No more generic AI copy that sounds like everyone else. Just plug in your product and get Meta-ready ad copy in 30 seconds. I'm giving away the full Meta Ad Copy Engine Gem for free. Want access? > Like the post > Comment "META" And I'll send it right over (must be following so I can DM)