Fakhr
@iamfakhrealam • 36,323 subscribers
CONTENT CREATOR | AI | Tech | Collaboration | DM open for Promo | WORKED WITH 1000+ AI COMPANIES 👉🏻 [email protected]
Shorts
Videos
I built a Halloween game in minutes, and AI made everything: the code, the art and the music 👻🎃 "Candy Ghost": fly through a spooky town, dodge the bats and grab the candy. All inside one app: Quadcode AI Here's the full workflow so you can build your own 👇 𝗦𝘁𝗲𝗽 𝟭: 𝗕𝘂𝗶𝗹𝗱 𝘁𝗵𝗲 𝗴𝗮𝗺𝗲 Pick the Developer agent + Claude Sonnet 5 and send: "Build a browser game called Candy Ghost using HTML, CSS and JavaScript in one file. A cute ghost flies through a spooky town at night. Space or tap to float up, let go to drop. Fly through gaps between haunted trees and chimneys, dodge bats, collect candy. Speed slowly increases. Add a score, a start screen and a 'BOO! Try again' Game Over screen. Cute Halloween colors. Make it fill the whole window with a Full Screen button. Use placeholder shapes so I can add images and sounds from an /assets folder later." 𝗦𝘁𝗲𝗽 𝟮: 𝗠𝗮𝗸𝗲 𝘁𝗵𝗲 𝗮𝗿𝘁 Click the image button, pick an image model and send: "Create a cute, friendly white ghost with big eyes, cartoon game style. Transparent background, facing right. Save it as assets/ghost.png" "Create a wide Halloween night background: a cute spooky town with a full moon and glowing pumpkins. Save it as assets/background.png" 𝗦𝘁𝗲𝗽 𝟯: 𝗠𝗮𝗸𝗲 𝘁𝗵𝗲 𝘀𝗼𝘂𝗻𝗱 Click the audio button, pick an audio model and send: "Create a fun Halloween music track with spooky organ and bouncy beats, about 20 seconds, that loops. Save it as assets/music. mp3" "Create a short, cute whoosh sound. Save it as assets/whoosh. mp3" 𝗦𝘁𝗲𝗽 𝟰: 𝗣𝘂𝘁 𝗶𝘁 𝗮𝗹𝗹 𝘁𝗼𝗴𝗲𝘁𝗵𝗲𝗿 Back to the Developer agent: "Use ghost.png and background.png in the game. Play music. mp3 on loop after Play, and whoosh. mp3 every time the ghost floats up." That's it. Code, images and sound in one app, and it has video and 3D models too. Try it:
Fakhr86,497 Aufrufe • vor 27 Tagen
AI movie hits 10M views on YOUTUBE in 8 days I checked that movie description And found the tool he used 👇
Fakhr63,115 Aufrufe • vor 1 Monat
I gave Space Bunny an ASCII wireframe and told it to compile it into a working dashboard. the ascii map was the entire spec. exact 250px sidebar, responsive grid, live charts on a 2-second mock telemetry loop. It reproduced the layout pixel-for-pixel and wired up all the state: sidebar nav, profile dropdown, table filters, just in first try. The part that got me: most models approximate layouts from descriptions. this one treated an ascii diagram like a blueprint. It also surprised me with the fast speed in responses and task handling. The provider is still anonymous, no lab has claimed it yet. free for 7 days only, go build something fun👀
Fakhr51,702 Aufrufe • vor 1 Monat
tencent hunyuan just shipped their third major model in six months. that pace is hard to keep up with. Hy4 preview is now live in workbuddy, and it's fully open source. the specs: 770B total params, 49B active, 1M+ token context window. but the number that matters is where it's pointed — real work. coding, office tasks, research, documents. here's the part i find interesting. tencent didn't build this in isolation. they put the training data together with their own experts across software engineering, gaming, finance and security, then designed the model side by side with products like workbuddy. model and product shaping each other instead of one being bolted onto the other. and it shows up in testing. 163 internal experts ran a blind test across 203 engineering tasks. hy4 preview scored 2.99/4 — ahead of kimi k3 at 2.94 and glm 5.3 at 2.92. on public benchmarks it clearly beats glm 5.2 and sits about level with glm 5.3. then the pricing. $6 per million input tokens, $18 per million output, $0.3 per million on cache hits. flagship results at a price you don't have to think about. and for the next two weeks it's free inside workbuddy.
Fakhr55,316 Aufrufe • vor 1 Monat
Turn a simple idea into a full game scene in minutes 🎮✨ I made this with Rosebud AI → Used GPT-5 to turn my prompts into a complete story: 1️⃣ Click Video Generate 2️⃣ Set your scene 3️⃣ Enter your prompt 4️⃣ Keep adding scene after scene This will only get better with the future Genie 3 from Google. Play my game: Use it just for fun or integrate it into your business for marketing. So many possibilities! 📹 Tutorial on how I did it ⬇️
Fakhr241,301 Aufrufe • vor 1 Jahr
Meet live AI Meet Lucy 2.5 Meet the most advanced live AI model! just tried it, result is cool...
Fakhr20,003 Aufrufe • vor 3 Monaten
PAI from Utopai Studios is raising the bar for AI video While most generators create disconnected scenes with no real story logic, PAI is the first long-form storytelling model focused on narrative continuity. It plans the full story arc in advance so everything actually connects. The results speak for themselves. Utopai Studios
Fakhr26,994 Aufrufe • vor 6 Monaten
