VIDraft (VIDraft)

fantos

posted an update about 3 hours ago

Post

24

# 🇰🇷 Korea AI Ecosystem at a Glance! Hugging Face Heatmap Leaderboard

Hello! 👋

We're excited to announce the **Heatmap Leaderboard** that visualizes Korean AI organizations' activities on Hugging Face **at a glance**!

## 🎯 Key Features

**📊 Real-time Activity Tracking**
- 94 unique colors for each organization
- Daily commit activity heatmap visualization
- Easy comparison of total contributions by organization

**🏢 Featured Organizations**
- 🦁 Major Enterprises: Samsung, Naver, Kakao, SKT, LG AI, NCSOFT
- 🚀 Startups: VIDraft, Upstage, Moreh, OnomaAI, GINIGEN, GINIPICK
- 💡 Community: openfree, aiqcamp, cutechicken, kolaslab, seawolf2357, and more

**🎨 Technical Highlights**
- Golden Ratio-based color distribution algorithm
- Built with Next.js + TypeScript + Bun
- Real-time data fetching

## 🔥 Why We Built This?

Visualizing Korea's AI community contributions on Hugging Face to understand:
- 🌟 Who's most actively contributing
- 📈 Trends over time
- 🤝 Collaboration and competition landscape

## 🚀 Check It Out Now!

fantos/Heatmap-Leaderboard-KOREA

Want to add your organization? Let us know in the comments! 🙌

#HuggingFace #KoreaAI #Leaderboard #Heatmap #OpenSource #AIVisualization

ginipick

posted an update 14 days ago

Post

1986

🍌 Huggwarts Banana - Nanobanana + Long-form Text Rendering Add-on

🎯 The Critical Flaw in Nanobanana
Google's Nanobanana is excellent, but has one critical weakness:
Long-form text rendering breaks easily.
Huggwarts Banana = Nanobanana + Long-form Text Rendering Add-on

ginigen/AI

✨ Core Value
🔥 Nanobanana's Foundation

Text-to-Image generation
Multiple image models
Style customization
High-quality outputs

🎨 + Our Add-on Enhancement
100% Backward Compatible - Use it exactly like Nanobanana!

🚀 Extended Features
📌 1. Perfect Long-form Text Rendering

Natural line-breaking for lengthy sentences
Full multilingual support (Korean, English, Japanese, Chinese, etc.)
Complex character combinations (double consonants, compound vowels, special symbols) handled flawlessly
Mixed emoji 😊 and special characters ♥
8 optimized fonts

🎬 2. Auto Image-to-Video Conversion
One-click video generation
Up to 12 seconds video length
Auto-applied effects: fade-in, zoom, slide transitions
SNS-optimized formats: 9:16 (Reels), 1:1 (Feed), 16:9 (YouTube)

🎨 3. Advanced Text Effects
Gradient colors: rainbow to subtle color transitions
Shadow effects: 3D depth perception
Neon glow: eye-catching luminous text
Custom backgrounds: AI-generated or custom upload

📐 4. Multiple Aspect Ratios
16:9 / 9:16 / 1:1 / 4:3, 3:4, 3:2, 2:3

🎯 5. Smart Model Selection
Automatic optimal model selection
Text-focused vs. Image-focused modes
Reference image support
High-resolution output (up to 4096x4096)

💡 Simple 4-Step Workflow
1️⃣ Input Text → English/Korean/Multilingual/Mixed content
2️⃣ Select Style → Font, color, effects
3️⃣ Generate Image → 10-30 seconds
4️⃣ Convert to Video (Optional) → One-click automation

🎯 Use Cases
✅ SNS Creators - Long-form text Reels/Shorts production
✅ Marketers - Rapid text-based promotional images/videos
✅ Educators - Visual text learning materials

openfree

updated a Space 28 days ago

2

Wan2.2 14B Fast

🎥

Wan_VO- generate a video from an image with a text prompt

openfree

updated a Space about 1 month ago

3

K-AI 커뮤니티 허브

👁

Powered by VIDraft

openfree

updated a Space about 2 months ago

2

Darwin Qwen3-4B

🌖

Chat with Darwin-Qwen3-4B evolutionary merged model

openfree

published a Space about 2 months ago

2

Darwin Qwen3-4B

🌖

Chat with Darwin-Qwen3-4B evolutionary merged model

openfree

posted an update about 2 months ago

Post

1831

🌱 Darwin-Qwen3-4B Released!
We are excited to introduce the first achievement of the Darwin Project. We have evolved an embryonic model that simultaneously inherits the strengths of both non-reasoning models and reasoning models based on Qwen3-4B, creating a new offspring model.

openfree/Darwin-Qwen3-4B

✅ Benchmarking results confirm that the traits and advantages of both parent models are fully reflected.
✅ We are releasing Darwin-Qwen3-4B on Hugging Face.

🔬 Technical Specifications

Model Configuration
-Base Architecture: Qwen3-4B
-Parent Model 1: Qwen/Qwen3-4B-Instruct-2507
-Parent Model 2: Qwen/Qwen3-4B-Thinking-2507
-Merge Algorithm: Darwin A2AP Enhanced v3.2
-Optimization Method: Evolutionary Algorithm with Adaptive Fitness

Evolution Process
-Population Size: 20 individuals
-Evolution Cycles: 5,000+ generations
-Fitness Objectives: Multi-objective optimization (accuracy, robustness, generalization)
-Validation Metric: 88.56% on proxy task (digit classification)

📊 Technical Innovations
1. Automated Model Merging
Automatic exploration of optimal merge ratios without manual hyperparameter tuning
Architecture-aware parameter alignment
Late-stage performance optimization

2. Cost Efficiency
Creation of new models at 1/10,000 the cost of foundation model training
Repeatable experimental process

🔮 Significance and Outlook
Darwin-Qwen3-4B demonstrates a new model creation paradigm: "Foundation A + Foundation B = Foundation A×B+C". This represents:

-Instant Domain Fusion: Immediate integration of models with different characteristics
-Sustainable AI Development: Reduced environmental burden through existing model recycling
-Democratized AI Research: Small research teams can create new models

📚 Additional Resources
GitHub Repository: [Coming Soon]
Technical Paper: [In Preparation]

openfree

updated a Space about 2 months ago

ROBO-R1984

🔥

Reasoning + Multimodal + VLM + Deep Research + Agent

openfree

published 3 Spaces about 2 months ago

XRAY

🏃

Download, visualize, and analyze X-ray baggage dataset

ROBO-R1984

🔥

Reasoning + Multimodal + VLM + Deep Research + Agent

Gpt2 Bert

📊

Generate text using a merged GPT2-BERT model

openfree

published a Space 2 months ago

DarwinAI Gemma 3 270m

😻

Generate text based on a prompt

openfree

updated a Space 2 months ago

DarwinAI Gemma 3 270m

😻

Generate text based on a prompt

openfree

posted an update 2 months ago

Post

2611

🔄 GitHub ↔️ HuggingFace Bidirectional Repository Converter + AI Auto Interface Generation

🎯 Three Magic Features in One Click
Move GitHub repositories to HuggingFace Spaces and Spaces back to GitHub freely, while AI automatically creates web interfaces for you.

openfree/Github-Transfer

🧠 AI Perfectly Understands Your Code
Project DNA Analysis
When you upload a repository, AI scans the entire structure. It comprehensively analyzes dependencies in requirements.txt, descriptions in README, code patterns, and model files to understand the essence of your project.
Auto-Generated Custom Interface
Computer vision projects transform into image upload and visualization interfaces, NLP projects into text input and generation options, audio projects into recording and waveform displays. Not templates, but optimized custom UI for your project.
LLM Fine-tunes Every Detail
Fireworks AI's large language model carefully configures parameter slider ranges, input validation, error handling, and result formatting. The demo looks as polished as if an experienced developer created it.
🔄 The Power of Bidirectional Conversion
GitHub to HuggingFace
A model completed on GitHub in the morning becomes a live web demo shared at lunch. AI automatically generates the Gradio interface, eliminating the need for separate frontend development.
HuggingFace to GitHub
Code experimented and improved in Spaces exports to GitHub for version control in the evening. Collaborate with team members through PRs and connect to CI/CD pipelines.

💡 Experience the Real Conversion Magic
🚀 AI Smartly Resolves Dependency Conflicts
✨ Real Automation That Saves Developer Time

🎬 You develop, AI deploys and demos!
Move freely between GitHub and HuggingFace, showcasing your projects with perfect AI-generated interfaces 🚀

ginipick

posted an update 2 months ago

Post

4285

🍌 Nano Banana + Video: AI Image Style Transfer & Video Generation Tool

🎨 Key Features
1️⃣ Image Style Transfer

ginigen/Nano-Banana-Video

📸 Upload up to 2 images for style fusion
✨ High-quality image generation with Google Nano Banana model
🎭 Apply desired styles with text prompts

2️⃣ Video Generation

🎬 Convert generated images to videos
📐 Maintain original aspect ratio option
⏱️ Adjustable duration (1-4 seconds)

🚀 How to Use
Step-by-Step Guide
Step 1: Image Generation 🖼️

Enter style description
Upload 1-2 images (optional)
Click "Generate Magic ✨"

Step 2: Video Creation 📹

Send generated image to video tab
Set animation style
Generate video!

💡 Use Cases

🏞️ Transform landscape photos into artistic masterpieces
🤖 Bring static images to life
🎨 Mix styles from two different images
📱 Create short videos for social media

⚡ Tech Stack
Google Nano Banana Stable Video Diffusion Gradio Replicate API

#AIVideoGenerator #ImageToVideoConverter #StyleTransferAI #GoogleNanoBanana #StableVideoDiffusion #AIAnimationTool #TextToVideo #ImageAnimationSoftware #AIArtGenerator #VideoCreationTool #MachineLearningVideo #DeepLearningAnimation #HuggingFaceSpaces #ReplicateAPI #GradioApplication #ZeroGPUComputing #AIStyleMixing #AutomatedVideoProduction #NeuralStyleTransfer #AIPoweredCreativity

openfree

posted an update 2 months ago

Post

13632

🍌 Nano Banana: Google AI Completely Free!

🎉 Finally, Google's Nano Banana AI is available for everyone - absolutely FREE!

🎯 Choose Your Perfect Version!
🌟 Free Nano Banana - For Everyone
Transform images with AI - It's that simple!

🚀 Start in 3 Seconds
1️⃣ Click Here 2️⃣ Upload Image 3️⃣ Enter Style → Done! ✨
No Sign-up ❌ | No Payment ❌ | No Ads ❌ | Just Free ⭕

📸 Simple drag & drop upload
✏️ Describe styles in any language
⚡ Results in under 30 seconds
🎨 Perfect for SNS, blogs, presentations

👉 Start Now: openfree/Free-Nano-Banana
🔍 Nano Banana Upscale - For Designers
Professional high-resolution output when you need it!

🖼️ 4x resolution upscaling (Real-ESRGAN)
🎯 Optimized for print & large displays
💎 Premium quality with preserved details
📐 Professional quality without Photoshop

👉 Create in HD: openfree/Nano-Banana-Upscale
💻 Nano Banana API - For Developers
Power your app with AI!

🔧 Instant RESTful API integration
📦 Python, JS, Java code examples included
⚙️ Batch processing & automation support
🚀 Unlimited usage with free API key

👉 Get API Access: aiqtech/Nano-Banana-API
🔗 Powered by Google's Official Model via Replicate API!
📌 100% Transparent Open Source
✨ We've integrated directly with Google's official Nano Banana model through Replicate API!

🔓 Full source code available on GitHub
📝 Complete Gradio interface implementation
🛠️ Detailed Replicate integration documentation
🎯 Fork and create your own version anytime

🚀 Start Your Journey Today!
Democratizing AI Technology - Built Together by the Community 💜
Made with ❤️ by Openfree AI Community
All code is open source. Let's grow together!

11 replies

·

ginipick

posted an update 2 months ago

Post

3664

🎉 Fashion Fit 360: The New Standard in AI Virtual Try-On!

🚀 Now Live and Free to Use!Say goodbye to online shopping uncertainty - "Will this look good on me?" - with our revolutionary solution!Fashion Fit 360 is a cutting-edge AI-powered virtual fitting service that transforms your fashion shopping experience.

LINK: ginigen/Fashion-Fit360

✨ Core Features
🔄 360-Degree Multi-Pose Generation
Transform a single front-facing photo into 6 different viewing angles!
Front, side, and back views for complete visualization
Experience a real fitting room mirror effect
Check fit and style from every perspective

👗 15 Fashion Item Categories
Apparel: Tops, bottoms, dresses
Jewelry: Necklaces, earrings, rings, bracelets
Accessories: Sunglasses, eyewear, hats, ties, bow ties, belts
Essentials: Bags, shoes

🎯 Perfect For:
🛍️ Online Shopping Enthusiasts: Preview before purchase - zero return hassles!
💍 Jewelry Lovers: Virtually try expensive pieces before investing
🎁 Thoughtful Gift-Givers: Test items on recipient photos beforehand
👔 Business Professionals: Preview suit and tie combinations
👗 Fashion Designers: Rapidly visualize design samples

💡 Why Fashion Fit 360?Fashion Fit 360 delivers innovation beyond conventional services.While most virtual fitting platforms only support clothing, we offer complete support for 15 accessory types. Unlike competitors providing only front views, Fashion Fit 360 generates 6 poses for true 360-degree visualization, ensuring you can verify actual fit perfectly.Performance is unmatched - get results in under 20 seconds with one-click simplicity and no complex configurations. Plus, download all generated images as a convenient ZIP file, eliminating tedious individual saves.

🔥 Key Differentiators
🎨 360-Degree Multi-Pose Image Generation
🤖 FLUX.1-Fill based OmniTry integrated model with Flux.1 KONTEXT LoRA technology

openfree

posted an update 2 months ago

Post

5818

🔒 Ansim Blur: Privacy-First Face Blurring for the AI Era

🚨 The Privacy Crisis is Now
Smart CCTVs 📹, delivery robots 🤖, and autonomous vehicles 🚗 are everywhere. Your face is being captured, transmitted, and stored without your knowledge or consent.

openfree/Face-blurring

The privacy threat is real:
24/7 surveillance cameras recording your every move
Companies harvesting facial biometric data at scale
Your face becoming a commodity without your permission

💡 The Solution: Ansim Blur
Real-time face anonymization powered by YOLOv8 🎯
✅ Process images, videos, and live streams
✅ Automatic GPU/CPU detection for universal deployment
✅ Choose between Gaussian blur or mosaic pixelation
✅ Fine-tune detection sensitivity for your needs
✅ Preserve audio tracks in video processing
🛡️ Real-World Applications
Enterprise Use Cases

Privacy compliance for robotics and drone footage
CCTV feed anonymization for regulatory requirements
Customer data protection in retail analytics

Personal Protection

Anonymize bystanders before sharing content online
Protect family members' privacy in shared videos
Avoid portrait rights issues in content creation

📊 Technical Specifications

Model: YOLOv8-face (optimized variant)
Performance: 30fps real-time processing on RTX 3060
Accuracy: 95%+ face detection rate
Formats: JPG, PNG, MP4, AVI, MOV

🌍 Why This Matters
"Face blurring will become mandatory for all public-facing cameras"
With GDPR in Europe, CCPA in California, and similar regulations worldwide, biometric data protection is becoming non-negotiable. Soon, every camera-equipped system will require built-in face anonymization capabilities.
🤝 Join the Movement
Why open source?
Because privacy isn't a premium feature—it's a fundamental right.

As technology advances, so must our commitment to privacy protection 🛡️

2 replies

·

openfree

posted an update 2 months ago

Post

7365

🤖 Global AI News Stream - 100% Unmanned AI News Automation Platform

🚀 Fully Automated News Generation with Just One Keyword!
Link: openfree/News-AI

🎯 Incredibly Simple: Just Enter a Keyword or URL!
✨ One Input, Complete Automation! ✨
Simply enter one keyword or one URL, and the system springs into action! 🚀 From web crawling to AI analysis, article writing, image generation, and auto-publishing - everything happens automatically.
Examples:

💬 Type "GPT-5" → Instant GPT-5 news article generation!
🔗 Paste "https://openai.com/blog/..." → Auto-extracts keywords from URL and creates related articles!
🎯 Enter "Tesla Bot" → Latest Tesla Bot developments instantly generated!

💎 Key Features - One Input, Everything Done!
🔍 Smart Keyword/URL Processing
Just type a keyword or paste any website URL! The system automatically extracts core keywords and gathers all relevant information to generate complete news articles. For URLs, it intelligently parses keywords from domains and paths.

🕷️ Instant Web Crawling
Based on your keyword or URL input, Brave Search API kicks in immediately! It collects real-time global AI news and automatically filters HOT news with relevance scores above 90 🔥 Just sit back and watch!

🧠 AI Analysis Starts Instantly
Within 3 seconds of keyword input, NLP analysis begins! It automatically analyzes collected data, verifies credible sources, and selects only the most relevant information. No complex setup needed - just your keyword!

✍️ One-Click Article Generation
Hit the "🔎 Generate Article" button and everything starts! Fireworks AI's GPT models create professional, natural articles based on your keyword. 500-800 words of polished content generated automatically.

🎨 Custom Image Auto-Generation
Flux-schnell AI automatically creates images perfectly matched to your keyword! High-quality visuals are generated automatically, tailored to the article category and content - no additional input needed.

1 reply

·

openfree

posted an update 3 months ago

Post

5678

🤖 AI-Generated 6-Nation Military Simulator in a Single HTML File

🚀 Project Highlight
A full-scale military strategy simulator that runs in a single HTML file! This AI-generated wargame implements real military equipment and tactical doctrines from 6 nations (🇰🇷,🇰🇵,🇺🇸,🇷🇺,🇺🇦,🇨🇳) using pure JavaScript only, without any external libraries.

openfree/WAR-Game-Simul

💡 Amazing Achievement of AI Auto-Generation

📁 Single File Magic
One-Click Launch: Just open the HTML file and play instantly
Zero Dependencies: No npm, webpack, or external libraries
Pure Vanilla JS: Implemented with Canvas API only, no frameworks
All-in-One: Rendering, physics engine, AI, and UI in a single file

🎮 Advanced Features AI Implemented
✅ Perlin Noise terrain generation algorithm
✅ Marching Squares contour rendering
✅ Lanchester combat equations
✅ A* pathfinding algorithm
✅ Real-time Line of Sight (LOS) calculations
✅ 40-second battlefield sound loop
🎖️ Implemented Military Systems
🔥 Real Weapon Systems from 6 Nations (100+ Units)

Real tanks: K2 Black Panther, M1A2 Abrams, T-90M
Attack helicopters: Apache, Ka-52, WZ-10
MLRS systems: HIMARS, Chunmoo, BM-21 Grad
Actual performance specs for each nation's unique equipment

⚔️ Realistic Combat Mechanics

Urban Warfare: 70% damage reduction for defenders, 2.5x road mobility
Mountain Combat: 20% range bonus from high ground, ridge defense bonus
Encirclement: Instant victory with 4+ units from 3+ directions
Real-time Combat: 10 engagement calculations per second

📊 Technical Achievement of AI-Generated Code
javascript// Everything in a single file!

🏆 New Standard for AI Wargame Generation
This project proves that AI can auto-generate complex military simulations in a single HTML file. It implements all core mechanics of AAA strategy games using pure JavaScript without any external dependencies.

#AIGenerated #SingleFile #Wargame #NoFramework #VanillaJS #ZeroDependency #HTML5Game #MilitarySimulator

7 replies

·

VIDraft

AI & ML interests