Kimi K2.6 just cooked Claude on design 😭 Same... prompt. Completely different output. I asked both to build a cinematic, scroll-driven indie game page. Dark. Editorial. Premium. Here's the exact prompt and what happened 👇show more

How I built with Claude 👇 1. Prompt: "Build... a storytelling website where each scroll section reveals a new chapter with fluid color transitions" 2. Use Three.js for the painted texture background that reacts to cursor 3. Prompt: "Add GSAP ScrollTrigger so each section animates in as a cinematic scene" 4. Use Lenis.js for that buttery smooth scroll that premium sites haveshow more

How I built with Claude 👇 1. Prompt: "Build... a storytelling website where each scroll section reveals a new chapter with fluid color transitions" 2. Use Three.js for the painted texture background that reacts to cursor 3. Prompt: "Add GSAP ScrollTrigger so each section animates in as a cinematic scene" 4. Use Lenis.js for that buttery smooth scroll that premium sites haveshow more

Everyone says “Gemini 3 can make games.” So we... tested it — with a Metal Slug-style prompt on both Gemini and Gambo. Same input. Completely different output. Here’s the result. #gemini3 #gemini_for_gameshow more

Hey... so... Claude Code is really good at design??... 👀 This was a ONE SHOT PROMPT. 🤯 We always asked Lovable to build "Design System" pages for our apps and they were always meh. We asked Claude Code to take a swing at it just based on our logo, a font, and brand colors. This is... really, really good for a one-shot prompt.show more

Kimi K3 vs Claude Fables 5 Two models walked... into a kitchen… and somehow made two completely different cookies. Which one are you taking a bite of? Prompt in the threads. 👇show more

Look at the difference the tool AND the prompt... make. Bad generator + lazy prompt: stiff movement, dead eyes, that obvious "AI look" everyone scrolls past. Seedance + a detailed, structured prompt: natural movement, real lighting, real pacing — looks like it came off an actual production shoot. Same product photo. Completely different result. It's not one or the other. You need the right tool AND the right prompt to get agency-level output. Ready to see the exact setup? Check the comments 👇show more

CLIENT ASKED 20 YEAR OLD TO BUILD A "SIMPLE"... WEBSITE THIS IS WHAT IT DELIVERED most websites look like this: -> Hero section -> Some text -> A few buttons -> Done Claude had other plans Here's what it built: -> Cinematic landing page with immersive animations -> Interactive particle effects -> Smooth scroll storytelling -> Premium UI inspired by Apple and luxury brands -> Responsive design without sacrificing performance → Production ready code in minutes the crazy part? there was no design agency no frontend team no weeks of back and forth revisions just one prompt and Claude Code while most developers are using AI to autocomplete code others are using it to build experiences that would've taken an entire team the gap isn't AI anymore it is imagination Bookmark this before every website starts looking like thisshow more

Can you tell the difference? I tested the exact... same prompt, same scene, and identical luxury perfume commercial in Seedance 2.0 4k on EaseMate AI_Official , comparing 4K and 1080p output. From the Mediterranean lighting and glass reflections to skin texture and cinematic depth of field, the difference is clear when viewed side by side. Which version would you choose for your next commercial—4K or 1080p? 👇 Prompt in the comments.show more

Seedance 2.5 is officially available on CapCut. To test... it, I used the same cinematic prompt in Seedance 2.5 and Seedance 2.0 and compared the results side by side. With support for up to 30-second generation, 50 reference materials, infinite scene extension, and frame-precise editing, Seedance 2.5 gives creators much more control over complex cinematic videos. Same prompt. Same settings. Watch both generations and see how they compare in prompt accuracy, motion quality, and cinematic consistency.show more

Claude feels kinda overhyped tbh. I tested the same... website design prompt on both Gemini and Claude many times. And every time Claude’s output wasn’t even close to the original. Meanwhile, Gemini got almost identical results, and after a few tweaks, it hit ~99% accuracy. Makes me wonder… maybe models just perform better on ecosystems they’re trained closer to? 🤔 Either way, Gemini is seriously outperforming in frontend dev right now. Remix:show more

FABLE 5 + HIGGSFIELD TURN A $35,000 ANIMATED SITE... INTO A ONE-SESSION, $12 BUILD. HERE'S EXACTLY HOW. a studio runs this across four people and three weeks. you run it across one chat window and one afternoon. THE BUILD, STAGE BY STAGE: STAGE 1 - THE CONCEPT Claude reads your brief and scripts the scroll before a line of code exists - what the visitor feels at second 3, 15, 40. prompt: "read this brief. script the scroll beat by beat, then scaffold the project with GSAP ScrollTrigger + Lenis." STAGE 2 - THE VISUALS (Higgsfield) every hero shot, transition, and ambient loop comes out of 30+ generative models - matched to the story, not pulled from a stock library. prompt: "generate the hero sting and one b-roll clip per section. 3-5s, high-res, cinematic." STAGE 3 - THE MOTION (Claude Code) Claude writes the ScrollTrigger timelines and Lenis smooth-scroll, extracts frames, optimizes every asset. zero hand-coded keyframes. prompt: "wire the scroll: pin the hero, scrub the video, reveal each section on scroll. keep it 60fps on mobile." STAGE 4 - THE POLISH six cinematic effects baked in, no config: film grain, particles, vignette, glass cards, color tints, scroll pacing. prompt: "bake in the cinematic layer, then QA load speed, mobile breakpoints, and whether the scroll actually lands - rewrite what doesn't." CONNECT HIGGSFIELD (MCP): add it as a custom connector in Claude Code: mcp_servers: higgsfield: url: " one OAuth flow. Claude generates and pulls clips directly - no exporting by hand. THE MATH: → what a studio charges: $6,000-$35,000+ → what it costs you: a Claude sub + a few dollars of Higgsfield credits → what it takes: 4 people + 3 weeks → 1 operator + 1 session the pipeline was the moat. it just became four prompts. Follow me, comment "MATH" and I'll send you the full step-by-step Playbook. full breakdown in the article 👇show more

We tested a lot of design skills in Codex... and other AI agents. They fix the old AI slop. But they often create a new one: the “taste skill look.” - Same premium sections. - Same editorial typography. - Same generated-design smell. Open Design does not rely on one taste prompt. It combines skills, systems, critique loops, and local harnesses to make AI pages feel less generated and more designed. This page was generated directly in Open Design.show more

🚨 Everyone's talking about ChatGPT Agents. But what happens... when you ask two agents to create a pitch deck? I ran the same prompt in Genspark and ChatGPT Agent. The results? Wildly different. Let me show you what happened 👇show more

Same reference image. Same prompt. Different models. I put... MiniMax H3 and Seedance 2.0 head-to-head on Pollo AI to see how each handles the exact same scene. Also excited that Seedance 2.5 is coming soon on PolloAI Check it out 👇show more

This might be the craziest way I’ve ever used... AI Agents. I gave MiniMax Design 2 iconic meme references and asked its AI Agent to connect them with one seamless cinematic FPV move. It analyzed the idea, broke down the sequence and built the MiniMax H3 prompt for me. The result is absolutely ridiculous. 🔥 I’m dropping the exact MiniMax Design prompt in the thread so you can try it yourself 👇 #MiniMaxH3 on #MiniMaxDesignshow more

I think AI Agents are about to completely change... how we prompt video models. I gave the MiniMax Design AI Agent one image and one simple instruction: “Act as an expert FPV director and turn this into something viral.” It analyzed the idea, built the camera logic, movement and pacing, then created a ridiculously detailed prompt for MiniMax H3. This is what came out. 🤯 And yes, I’m sharing the exact prompt + workflow in the thread 👇 #MiniMaxH3 on #MiniMaxDesignshow more

I gave Kimi K3 and Opus 5 the exact... same prompt to build a car racing game. I expected Opus 5 to take the lead. Instead, Kimi K3 finished in ~25 min for ~$8.9, while Opus 5 took 19 min and cost $14. The biggest surprise wasn’t the speed or the price. Kimi K3 built the better game. Smoother controls, better physics, and a driving experience that felt ready from the start. Opus 5 looked cleaner visually but Kimi won where it actually mattered. Nearly half the cost and the better gameplay.show more

Grok 4.5 in Grok Build created an FPS game... in under an hour. The prompt was simple. I told it to write a game design document and pull free assets from the web. Then I had it create a TODO.md with implementation phases and run a loop to build out each phase. SpaceXAI and Cursor cooked here. This model is insane.show more

This is wild. Higgsfield Games lets you build and... deploy a full multiplayer game from a single prompt. Any genre, 2D or 3D, with characters, props, and worlds generated on the fly. Powered by Claude Fable 5. Huge W for indie devs.show more