๐ฎ 3D Airforce Simulator - Web Browser 3D Fighter Jet Simulator
๐ Introduction A full-scale 3D aerial combat game created with VIBE CODING! ๐ฅ Enjoy realistic fighter jet simulation directly in your browser without any installation.
๐ฅ Pro Tips Missile Lock: Keep target in crosshair for 3 seconds ๐ฏ Missile Warning: Press F immediately for flares! ๐จ Vision Darkening: Level out to recover ๐๏ธ Over-G Warning: Don't overdo extreme maneuvers! โก
๐ป Tech Stack Three.js Vanilla JS Web Audio API Pointer Lock API
๐จ Power of VIBE CODING! Complete game engine in a single JS file! ๐
Real-time physics simulation โ๏ธ Complex AI behavior patterns ๐ง Professional HUD system ๐บ Immersive sound design ๐
๐ฎ Play Now! Browser only! Mouse required! ๐ฑ๏ธ
๐ Known issue: BGM autoplay restrictions in some browsers
Demo of OCR & Math QA using multi-capable VLMs like MonkeyOCR-pro-1.2B, R1-One-Vision, VisionaryR1, Vision Matters-7B, and VIGAL-7B, all running together with support for both image and video inference. ๐ช
Multimodal OCR with ReportLab? On Colab T4? (Nanonets OCR, Monkey OCR, OCRFlux 3B, Typhoo OCR 3B?) .. Yeah, itโs possible. Iโve made a dedicated Colab notebook to experiment with these models (all built on top of Qwen2.5 VL). ๐ค๐
๐ฒ When Biotech Meets Vegas = ?? Hey there! Today I'm thrilled to introduce something truly extraordinary. We've transformed DNA-Diffusion into a full-blown casino slot machine - welcome to DNA CASINO! ๐
๐ฏ What's This All About?
๐งฌ Generate 200bp DNA Regulatory Sequences: AI-powered generation of cell-type specific synthetic biology sequences ๐ฐ Slot Machine UI: Watch each nucleotide (A,T,C,G) spin like real casino reels! ๐ฌ Real-time Protein Analysis: Instantly translate generated DNA to protein and get AI-powered structure/function analysis
๐ซ Key Features 1๏ธโฃ Choose Your Cell Type (Like Casino Chips!) ๐ข K562 - Leukemia cell line ๐ต GM12878 - Lymphoblastoid cell line ๐ก HepG2 - Liver cancer cell line
2๏ธโฃ Pull the Lever to Begin! Just like a real slot machine - pull the lever or hit SPIN and watch 200 nucleotides whirl in spectacular fashion! ๐ช
3๏ธโฃ AI-Powered Protein Analysis
DNA โ Protein translation Structure/function prediction via vidraft/gemma-3-r1984-27b (ranked #2 in medical reliability on FACTS Grounding Leaderboard) Cell-type specific insights
๐ ๏ธ Tech Stack python๐จ Frontend: HTML/CSS/JS (Pure vanilla goodness!) ๐ง Backend: Gradio + DNA-Diffusion model ๐ค AI Analysis: vidraft/gemma-3-r1984-27b โก GPU Acceleration: Hugging Face Spaces GPU
๐ฎ How to Play
Pick your cell-type chip ๐ฏ Pull the lever or hit SPIN! ๐ฐ Watch your DNA sequence generate โจ Check out the protein analysis ๐ฌ
๐ What Makes It Special
Immersive casino theme: Neon lights, glowing effects, and that iconic 777 lever! Scientific accuracy: Real codon tables, precise protein translation Educational value: Learn DNA-protein relationships the fun way
๐ฏ Introduction A leaderboard that visualizes the vibrant HuggingFace community activity through heatmaps.
โจ Key Features ๐ Real-time Tracking - Model/dataset/app releases from AI labs and developers ๐ Auto Ranking - Rankings based on activity over the past year ๐จ Responsive UI - Unique colors per organization, mobile optimized โก Auto Updates - Hourly data refresh for latest information
๐ Major Participants Big Tech: OpenAI, Google, Meta, Microsoft, Apple, NVIDIA AI Startups: Anthropic, Mistral, Stability AI, Cohere, DeepSeek Chinese Companies: Tencent, Baidu, ByteDance, Qwen HuggingFace Official: HuggingFaceH4, HuggingFaceM4, lerobot, etc. Active Developers: prithivMLmods, lllyasviel, multimodalart and many more
๐ Value Trend Analysis ๐ Real-time open source contribution insights Inspiration ๐ช Learn from other developers' activity patterns Ecosystem Growth ๐ฑ Visualize AI community development
The bunch of comparable demos for Multimodal VLMs (excels in OCR, cinematography understanding, spatial reasoning, etc.) now up on the Hub ๐ค โ max recent till Jun'25.
The demo for Camel-Doc-OCR-062825 (exp) is optimized for document retrieval and direct Markdown (.md) generation from images and PDFs. Additional demos include OCRFlux-3B (document OCR), VilaSR (spatial reasoning with visual drawing), and ShotVL (cinematic language understanding). ๐ช
The community GPU grant was given by Hugging Face โ special thanks to them. This space supports the following tasks: (image inference, video inference) with result markdown canvas and object detection/localization. ๐ค๐
. . . To know more about it, visit the model card of the respective model. !!
๐ฌ How to Use Seedance, the #1 Video Generation Model, for Free
๐ A Hidden Gem I Stumbled Upon While browsing Hugging Face, I discovered an amazing project. I found ByteDance's Seedance video generation service - which knocked Google's VEO3 down to 2nd place on the video generation leaderboard - available for free on Hugging Face!
๐จ Flux-Kontext FaceLORA - AI Portrait Style Transfer
๐ Introduction Transform your photos into masterpieces! Flux-Kontext FaceLORA is an innovative AI-powered tool that converts portrait photos into various artistic styles using cutting-edge technology.
๐ธ Easy to Use: Upload photo โ Select style โ Click Generate! ๐จ 7 Art Styles: Famous painter styles including Van Gogh, Monet, Renoir ๐ค Face Preservation: AI maintains your facial features while transforming the style โก Fast Generation: Get results in seconds with ZeroGPU support ๐ฏ Custom LoRA: Use any LoRA model from HuggingFace
๐ผ๏ธ Available Styles
๐ฏ Studio Ghibli - Whimsical anime art style ๐ Winslow Homer - American realist watercolor ๐ป Van Gogh - Post-impressionist with swirling brushstrokes ๐ Paul Cรฉzanne - Geometric post-impressionist structure ๐ธ Renoir - Impressionist with soft luminous light ๐ชท Claude Monet - Impressionist light and color โ๏ธ Fantasy Art - Epic magical character portraits
๐ How to Use 1๏ธโฃ Upload your portrait photo 2๏ธโฃ Select an art style from gallery 3๏ธโฃ Add optional description 4๏ธโฃ Click Generate โจ button! ๐ก Pro Tips
๐ญ Front-facing photos work best ๐จ Adjust Style Strength for transformation intensity ๐ฒ Use Randomize seed for varied results ๐ Add descriptions for more detailed outputs
๐ ๏ธ Tech Stack
Model: FLUX.1-Kontext-dev by Black Forest Labs LoRA: Community-created style adapters Infrastructure: Hugging Face Spaces + ZeroGPU
๐ Start Creating Now! Create your unique AI portrait and share it on social media! #FluxKontextFaceLORA #AIArt #PortraitTransfer
๐ฏ The First Step Toward AGI SOMA (Self-Orchestrating Modular Architect) is a revolutionary architecture that fulfills the essential requirements for AGI (Artificial General Intelligence) Level 1. It perfectly implements the common AGI prerequisites emphasized by Yann LeCun (Meta), OpenAI, and Google DeepMind within a single LLM.
๐งญ Self-Orchestrating The ability to define problems and distribute roles without external instructions is fundamental. This is the actual implementation of OpenAI's "Agentic AI" concept, with built-in real-time self-regulation mechanisms.
๐งฉ Modular A single LLM internally creates multiple personas: ๐ฏ Planner = Supervisor AI establishes strategies ๐ก Creator = Presents innovative solutions ๐ Analyzer = Collects and analyzes data โ๏ธ Evaluator = Performs critical assessments ๐ Executor = Final synthesis and implementation This perfectly realizes Meta AI's proposed "World Model + Planner + Memory + Actor" structure.
๐ง Architect Capable of high-level thinking and problem structuring beyond simple execution. It actually implements the plan-adapt-multitask capabilities required by DeepMind's Gemini series, systematically decomposing and reconstructing complex problems.
The demo for DREX-062225-exp (Document Retrieval and Extraction eXpert ~ experimental) / typhoon-ocr-3b (a bilingual document parsing model built specifically for real-world documents) / VIREX-062225-exp (Video Information Retrieval and Extraction eXpert ~ experimental) / olmOCR-7B-0225-preview (the document parsing model based on Qwen2VL). ๐ค
Updated the docscopeOCR-7B-050425-exp with the DREX-062225-exp, with improved preciseness in table structure and line spacing in the markdown used on the document page. And though this is still an experimental one, it's expected to perform well in the defined DREX use cases [ Document Retrieval and Extraction eXpert โ experimental ocr ]. ๐ป
โก What is Self-Forcing? While traditional methods require 50-100 steps, Self-Forcing achieves the same quality in just 1-2 steps. Through self-correction and rapid convergence, this Distribution Matching Distillation (DMD) technique maintains quality while delivering 50x speed improvement.
๐ก Technical Advantages of Self-Forcing 1. Extreme Speed Generates 4-second videos in under 30 seconds, with first frame streaming in just 3 seconds. This represents 50x faster performance than traditional diffusion methods. 2. Consistent Quality Maintains cinematic quality despite fewer steps, ensures temporal consistency, and minimizes artifacts. 3. Efficient Resource Usage Reduces GPU memory usage by 70% and heat generation by 30%, enabling smooth operation on mid-range GPUs like RTX 3060.
๐ ๏ธ Technology Stack Synergy VEO3 Real-Time integrates multiple technologies organically around Self-Forcing DMD. Self-Forcing DMD handles ultra-fast video generation, Wan2.1-T2V-1.3B serves as the high-quality video backbone, PyAV streaming enables real-time transmission, and Qwen3 adds intelligent prompt enhancement for polished results.
๐ Performance Comparison Traditional methods require 50-100 steps, taking 2-5 minutes for the first frame and 5-10 minutes total. In contrast, Self-Forcing needs only 1-2 steps, delivering the first frame in 3 seconds and complete videos in 30 seconds while maintaining equal quality.๐ฎ Future of Self-Forcing Our next goal is real-time 1080p generation, with ongoing research to achieve
The demo for smoldocling / nanonets ocr / typhoon ocr / monkey ocr explores the document OCR capabilities of various newly released multimodal VLMs in a single space. And if you're experiencing or demoing long document image OCR, kindly use the Smoldocling 256M preview [ Smoldocling is back in demo here. ] ๐ค.
๐ Project Introduction Revolutionary AI presentation generator presented by OpenFree AI Community! Create professional-level PPTs with just a few clicks. ๐ Completely FREE! Create Premium PPTs with Free GAMMA! ๐
๐ค Powered by FACTS Grounding Leaderboard 2nd RANK LLM Base Model: vidraft/gemma-3-R1984-27B Perfect support for English/Korean/Multi-language Automatic speaker notes generation
๐ Smart Diagrams Process Flow, Concept Map, WBS, Radial, Synoptic Chart Content analysis-based automatic diagram generation Perfect Korean font support
๐ก Main Features
๐ Intelligent Content Generation Auto-generate 3-20 slides just by entering a topic Latest information through web search Reference PDF, CSV, TXT files
๐ผ๏ธ Visual Automation 3D images for cover & conclusion slides Auto-generate 2 content-based diagrams Add 2 FLUX style images
๐ฏ Customizable Design 5 professional themes 3 layout styles Automatic emoji mapping system
๐ฐ Premium Features for FREE! Create professional-grade presentations with Free GAMMA (Open GAMMA) that rivals paid PPT generation services! ๐
The demo for the MonkeyOCR Recognition model, which adopts a Structure-Recognition-Relation (SRR) triplet paradigm & Nanonets-OCR-s a powerful, state-of-the-art image-to-markdown OCR model that goes far beyond traditional text extraction and other experimental document OCR models, is combined into a single space.
๐ฌ VEO3 Directors - All-in-One AI Video Creation Suite
๐ What is VEO3 Directors? VEO3 Directors is a revolutionary end-to-end AI video creation platform that transforms your ideas into cinematic reality. From story conception to final video with synchronized audio - all in one seamless workflow!
๐ฒ Instantly generate creative story ideas across multiple genres ๐ Bilingual support (English/Korean) ๐ญ Rich categories: Genre, Setting, Characters, and more
๐ฅ AI Script & Prompt Crafting
๐ฌ Powered by Friendli API for Hollywood-quality prompts ๐ค AI Director writes detailed cinematography instructions ๐ฌ Professional elements: camera movements, lighting, VFX
๐ฌ Video + Audio Generation
๐จ Wan2.1-T2V-14B for stunning visual quality โก NAG 4-step inference - 10x faster generation ๐ต MMAudio auto-generates matching soundscapes ๐๏ธ Full control over resolution, duration, and style ๐ฌLLM(API): VIDraft/Gemma-3-R1984-27B
๐ก How It Works
Generate Story โ "The Time Traveler's Final Choice" ๐ฐ๏ธ Create Script โ AI writes cinematic scene descriptions ๐ Produce Video โ 4-8 second clip with synchronized audio ๐๏ธ
๐ฏ What Makes It Special
Unified Workflow: From idea to video in one interface Director-Level Prompts: Professional cinematography language Lightning Fast: Minutes, not hours Smart Audio: Context-aware sound generation
๐ Use Cases
๐ฑ Social Media Content ๐ Educational Videos ๐บ Marketing & Ads ๐ฎ Game Cutscene Prototyping ๐จ Digital Art Creation
Upload Image - Select your starting image Enter Prompt - Describe desired motion and style Adjust Settings - 8 steps, 2-5 seconds recommended Generate - Complete in just minutes!
๐ก Optimization Tips โ Recommended Settings: 8-10 steps, 576ร1024 resolution โ Prompting: Use "cinematic motion, smooth animation" keywords โ Duration: 2-5 seconds for optimal quality โ Motion: Emphasize natural movement and camera work ๐ FusionX Enhanced vs Standard Models Performance Comparison: While standard models typically require 15-20 inference steps to achieve decent quality, our FusionX Enhanced version delivers premium results in just 8-10 steps - that's more than 50% faster! The rendering speed has been dramatically improved through optimized LoRA fusion, allowing creators to iterate quickly without sacrificing quality. Motion quality has been significantly enhanced with advanced causal modeling, producing smoother, more realistic animations compared to base implementations. Detail preservation is substantially better thanks to MPS Rewards training, maintaining crisp textures and consistent temporal coherence throughout the generated sequences.
๐ Whisper-OCR Multilingual Translation Space ๐
Welcome! This Space takes English audio, video, images, and PDFs and instantly converts them into Chinese (ZH), Thai (TH), and Russian (RU)โno other source language required.
๐ค I'm leading 'Openfree AI', Korea's most prominent AI open-source community. First and foremost, I'd like to express my deepest gratitude for Hugging Face's continuous support and efforts. ๐ Our Openfree AI collaborates with various AI communities across Korea, contributing to knowledge sharing and ecosystem development. ๐ค I've been actively promoting the critical importance of Hugging Face as Korea's AI infrastructure backbone, engaging with senior government officials, National Assembly members, university leaders, and media executives to emphasize how Hugging Face represents Korea's AI future at a national policy level. I consider myself a 'voluntary Korean ambassador for Hugging Face'. ๐ฐ๐ทโจ Let me share our community's achievements on the Hugging Face platform over the past year: ๐ฏ
๐ Published hundreds of models and spaces ๐ฅ Surpassed 10 million cumulative visitors ๐ Achieved 1.7 million Monthly Active Users (MAU) ๐จ Generated over 1 million images/videos per month
These achievements were possible thanks to Hugging Face's generous support, including H200 resources. Thank you sincerely. ๐ ๐ I'm thrilled to share exciting news! This July, we'll host the "Hugging Face Forever" seminar at the Korean National Assembly, sponsored by AI policy lawmakers. ๐๏ธ Our community will organize this groundbreaking event focusing on 'Hugging Face and Community Contributions and Roles' - a truly meaningful and revolutionary milestone for Korea's AI ecosystem. ๐ซ We'll continue working hard for Korea's AI ecosystem development and... oh, if you ever need a Korean branch manager for Hugging Face, please let me know! ๐ (Just kidding... or am I? ๐ค) Thank you. ๐ค Openfree AI Representative ๐
