Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts

merveΒ 
posted an update 1 day ago
AdinaYΒ 
posted an update 1 day ago
view post
Post
1711
MiniCPM-V 4.5 πŸš€ New MLLM for image, multi-image & video understanding, running even on your phone, released by OpenBMB

openbmb/MiniCPM-V-4_5

✨ SOTA vision language capability
✨ 96Γ— video token compression > high-FPS & long video reasoning
✨ Switchable fast vs deep thinking modes
✨ Strong OCR, document parsing, supports 30+ languages
codelionΒ 
posted an update 1 day ago
view post
Post
2808
I recently added a recipe in ellora to improve reasoning capabilities to Gemma-3-1B using self-supervised learning. Model now shows step-by-step thinking in <think> tags before answering.

Logic puzzle accuracy: 61% β†’ 84%. 3 hours training on single GPU. 🧠

Used GRPO where model generates multiple responses and learns to prefer better reasoning. Works surprisingly well for making smaller models more transparent.

πŸ”— Colab: https://colab.research.google.com/github/codelion/ellora/blob/main/Ellora_Recipe_2_Reasoning_LoRA_with_Self-Rewarding_GRPO.ipynb

πŸ€— Model: codelion/gemma-3-1b-it-reasoning-grpo-lora

πŸ’» Code: https://github.com/codelion/ellora
  • 1 reply
Β·
ginipickΒ 
posted an update 1 day ago
view post
Post
804
πŸŽ‰ Fashion Fit 360: The New Standard in AI Virtual Try-On!

πŸš€ 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
πŸ”„ 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

πŸ‘— 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:
πŸ›οΈ Online Shopping Enthusiasts: Preview before purchase - zero return hassles!
πŸ’ Jewelry Lovers: Virtually try expensive pieces before investing
🎁 Thoughtful Gift-Givers: Test items on recipient photos beforehand
πŸ‘” Business Professionals: Preview suit and tie combinations
πŸ‘— Fashion Designers: Rapidly visualize design samples

πŸ’‘ 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.

πŸ”₯ Key Differentiators
🎨 360-Degree Multi-Pose Image Generation
πŸ€– FLUX.1-Fill based OmniTry integrated model with Flux.1 KONTEXT LoRA technology
openfreeΒ 
posted an update 1 day ago
view post
Post
3564
πŸ”’ Ansim Blur: Privacy-First Face Blurring for the AI Era

🚨 The Privacy Crisis is Now
Smart CCTVs πŸ“Ή, delivery robots πŸ€–, and autonomous vehicles πŸš— 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

πŸ’‘ The Solution: Ansim Blur
Real-time face anonymization powered by YOLOv8 🎯
βœ… Process images, videos, and live streams
βœ… Automatic GPU/CPU detection for universal deployment
βœ… Choose between Gaussian blur or mosaic pixelation
βœ… Fine-tune detection sensitivity for your needs
βœ… Preserve audio tracks in video processing
πŸ›‘οΈ 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

πŸ“Š 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 featureβ€”it's a fundamental right.

As technology advances, so must our commitment to privacy protection πŸ›‘οΈ
  • 2 replies
Β·
prithivMLmodsΒ 
posted an update about 21 hours ago
view post
Post
1816
OpenGVLab's InternVL3_5-2B-MPO [Mixed Preference Optimization (MPO)] is a compact vision-language model in the InternVL3.5 series. You can now experience it in the Tiny VLMs Lab, an app featuring 15+ multimodal VLMs ranging from 250M to 4B parameters. These models support tasks such as OCR, reasoning, single-shot answering with small models, and captioning (including ablated variants), across a broad range of visual categories. They are also capable of handling images with complex, sensitive, or nuanced content, while adapting to varying aspect ratios and resolutions.

✨ Space/App : prithivMLmods/Tiny-VLMs-Lab
πŸ«™ Model : OpenGVLab/InternVL3_5-2B-MPO
↗️ Collection: OpenGVLab/internvl35-68ac87bd52ebe953485927fb
πŸ—žοΈ Paper : https://arxiv.org/pdf/2508.18265
↗️ Multimodal Space Collection : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0

To learn more, visit the relevant spaces, collections, and model cards.
openfreeΒ 
posted an update 2 days ago
view post
Post
7130
πŸ€– Global AI News Stream - 100% Unmanned AI News Automation Platform

πŸš€ 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! πŸš€ From web crawling to AI analysis, article writing, image generation, and auto-publishing - everything happens automatically.
Examples:

πŸ’¬ Type "GPT-5" β†’ Instant GPT-5 news article generation!
πŸ”— Paste "https://openai.com/blog/..." β†’ Auto-extracts keywords from URL and creates related articles!
🎯 Enter "Tesla Bot" β†’ Latest Tesla Bot developments instantly generated!

πŸ’Ž Key Features - One Input, Everything Done!
πŸ” 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.

πŸ•·οΈ 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 πŸ”₯ 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 "πŸ”Ž 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
Β·
kanaria007Β 
posted an update 3 days ago
view post
Post
6109
βœ… New Article: *Relationships as Structured Reciprocity*

Title:
πŸ€β€―Relationships: Ethics as Cross-Construct Jump Series
πŸ”— https://huggingface.co/blog/kanaria007/structured-relationships

---

Summary:
Relationships are often framed as *emotion and chance*.
Structured Intelligence reframes them as *reciprocal cognitive architectures*:

* Trust and love as *reinforced feedback loops*
* Conflict as *constraint misalignment and jump failure*
* Growth as *loop stabilization through reflection and repair*

> Human connection isn’t mystery β€”
> *it’s structure that learns to align across minds.*

---

Why It Matters:
β€’ Reveals *how trust, betrayal, and repair follow structural patterns*
β€’ Bridges *psychology, sociology, and cognitive modeling*
β€’ Enables *AI that supports human connection without mimicry*

---

What’s Inside:
β€’ Relationships as *multi‑agent jump and memory loops*
β€’ *Attachment and reciprocity* as structural alignment
β€’ *Conflict resolution* as rollback and loop repair
β€’ Implications for *therapy, collaboration, and social AI*

---

πŸ“– Article 26 of the Structured Intelligence Series

Where Article 25 explored *psychology as structured mind*,
Article 26 extends this to *relationships* β€”
showing how *minds meet, align, and recover through structural loops*.

---

Next: Improvisation as Live Structural Navigation
The next article examines *how spontaneity and flow emerge as high‑frequency jump execution*,
revealing *why improvisation is structure forming itself under time pressure*.

> From bonds to moments,
> *structure carries the pulse of human connection and creation.*
MonsterMMORPGΒ 
posted an update 4 days ago
view post
Post
5693
Qwen Image Edit Full Tutorial: 26 Different Demo Cases, Prompts & Images, Pwns FLUX Kontext Dev

Tutorial Link
https://youtu.be/gLCMhbsICEQ

Extra Info
I tested newly arrived Qwen-Image-Edit-Lightning-8steps-V1.0 (arrived after tutorial recorded) and definitely our existing preset which uses Qwen-Image-Lightning-8steps-V1.1 is better than it, so this tutorial and presets are still 100% best quality and up-to-date

Info
Qwen Image Edit just has been published and since then I have been experimenting to prepare you this amazing tutorial. I have literally shown 26 unique cases and provided demo images and prompts. After watching this tutorial your image editing skills will move to next level i promise you that. Also this tutorial will give you a lot of ideas.
jeffboudierΒ 
posted an update 1 day ago
view post
Post
1682
Quick 30s demo of the new Hub > Azure AI integration to deploy HF models in your own Azure account. Now with Py and CLI!

GG @alvarobartt @kramp @pagezyhf