HF's Missing Inference Widget
Generate text responses using various AI models
Generate text responses using various AI models
Evaluate mathematical expressions using a chatbot
LLaMAX3 Translator
Mistral Nemo Demo
Need to analyze data? Let a Llama-3.1 agent do it for you!
Need to analyze data? Let a Llama-3.1 agent do it for you!
Generate images using text prompts
Generate chatbot responses using various models
LLM, chatbot, human-feedback
Chat with a language model using text input
Solatium provide free access to the latest LLM models.
Chat with images and text using a Japanese visual language model
Chatbot
Compare two chatbots and vote on the better one
Generate structured output from text prompts
Display a React app with TypeScript
GPT-4o, Claude...
Chat with any model on the Hub
Explore token probability distributions with sliders
Agents: Mozilla, AppleWebKit, Chrome, Safari, Edge
Explore and submit models for benchmarking
Generate text based on an image and prompt
Generate text responses using various language models
Generate text based on your input
Ask questions and get detailed answers with visual search graphs
Chat with AI with ⚡Lightning Speed
Generate chat responses using FalconMamba-7b model
Chat about images by uploading them
Answer questions using images and text
Interact with a chatbot using your README file
Chat with an AI assistant using different models
Chat with DeepHermes
Chat with LLaVA using images and text
Upload PDF, ask questions, get answers
Chat with your multilingual A.I. assistant.
Run SmolLM-360M-Instruct in realtime with MLC WebLLM
LLM for long context
Generate detailed descriptions from images and questions
Generate detailed text based on user input
Meta Llama3 8b with Llava Multimodal capabilities
Generate code and answers with chat instructions
Generate speech and translate audio using AI models
New SOTA small model from Microsoft, and multilingual!
Ask questions about images
Demo for MiniCPM-o 2.6 to answer questions about images
A powerful AI chatbot that runs locally in your browser
Convert text to audio and vice versa
Chat with your multilingual A.I. assistant.
Solve math problems from images
Chat with Gemini Pro and upload images for responses
chat with Shadow the Hedgehog, Quick brr
Generate text from an image and question
Generate text based on a prompt
Interact with a powerful AI chatbot for code and general questions
Chat with an Italian Small Model
Combine text and images to generate responses
Multilingual, Multimodal, Mighty 2B
Transcribe speech and generate AI response
Generate text responses from a chatbot model
Generate text from an image and question
On Device Large Action Models to plan and execute tasks
On Device Large Action Models : plan and execute tasks
One-stop-shop for frequently used models
Chat with Japanese Llama 3 Youko
Generate long-form text content based on prompts
Generate long-form text content
Chat with AI characters using their personas and quotes
Languages: Swahili, Yoruba, Hausa, isiZulu, and isiXhosa
AI Powered Chat
Ask questions and get detailed answers
Detect objects in images and get bounding boxes
Flux.1 Fill
state-of-the-art coding performance with fewer than 10 B
Upload a PDF and ask questions about its content
Get Lyrics from Genius's Link
Generate visual data analysis plots
Chat llama-cpp-agent that can search the web.
Real-time AI App with Groq API and LangChain
Groq API Playground
Generate images from text or images with enhanced prompts
Reflection-70B by Matt Schumer
Service unavailable, 405B recently taken off hub inference:/
Play chess between two AI models
Chat with Art 3B
Chat with advanced language models like ChatGPT
Chat with PDFs or use web search to answer questions
Track, rank and evaluate open LLMs in Portuguese
Get the price for any API LLM call.
Kobble Tiny
Calculate VRAM requirements for running LLM models
Uncensored General Intelligence Leaderboard
Convert text into tokens for multiple models
Command-R+ 08/2024 on serverless inference
Generate captions and analyze images with various tasks
Upload a PDF, ask questions, get insights
Generate an isometric grid with pathfinding
Access various AI tools and services
Display interactive web apps
Generate conversational responses using OpenAI's language model
Display leaderboard for model performance metrics
GOT - OCR (from : UCAS, Beijing)
Chat with an AI assistant
GPT 4o like bot.
Display a relocation message for GGUF Playground
Generate detailed step-by-step answers with a chatbot
Generate image descriptions using text prompts and image URLs
VCTK 109 Voices
Generate detailed, step-by-step responses to queries using AI
Describe and analyze images and videos
Generate answers from images and questions
Extract text from various document types
Describe and solve math problems from images or sketches
Interact with a chatbot that understands text and images
Give your space a voice! (Demo)
Generate a unique character and image based on world and persona descriptions
Qwen-2.5-72B on serverless inference
Qwen-2.5-3B on serverless inference
Generate captions for images in various styles and lengths
Set theme for Hugging Face Playground
Generate random prompts using powerful LLMs
Explore and filter language model benchmark results
Meta-Llama-3.1-70B-Instruct-AWQ-INT4
Translate English text to Japanese
N
Generate responses using advanced language models
Document Question Answering with ColPali & Pixtral
Extract and display content from URLs
Generate retrieval queries from document images
Chatbot with Unlimited Vision,Image generation and WebSearch
Detect and label objects in images
Retrieve images based on text queries
n
Evaluate open LLMs in the languages of LATAM and Spain.
Chat with a language model to get answers and assistance
Generate text by uploading images and asking questions
Chat with Meta Llama 3.2 (1B) for various tasks
Track, rank and evaluate open LLMs and chatbots
Generate Gradio code from UI
Chat about images with Meta Llama
Generate detailed descriptions from images and videos
Display a React app with TypeScript
Experimental workflow for story driven games and porting
Generate captions for images in various styles
Chat with Pixtral 12B using Mistral Inference
World's fastest Video Chat Assistant
Generate images and answer questions using text input
A powerful AI chatbot that runs locally in your browser
Evaluating LMMs on Japanese subjects
Update model card with Open LLM Leaderboard results
RAG with source links inserted using LXT library.
Translate text between 200 languages
VLMEvalKit Evaluation Results Collection
A tool for libraries, archives and museums
Benchmarking LLMs on the stability of simulated populations
View game stats and spectrograms
Chat with a Japanese language model
Chatbot
VLMEvalKit Eval Results in video understanding benchmark
multilingual instruct model verifiably trained on open data
interact with videos !
Pythia chatbotです。
Qwen
Explore toxicity scores of models
Vector Post Training Quantization Demo
Vector Post-Training Quantization (VPTQ) Demo
Chat with a language model to get answers and generate text
Chat with Mistral-Nemo
Convert text to SPLADE token scores
Qwen7bチャットボット
Bakuチャットボットです。
Process images to visualize features and masks
NemoAligner Synthetic SFT with function calling
NSFW Text Generator for Detecting NSFW Text
Translate text from one language to another
Chat with Salamandra AI
This is an official demo website for open-o1.
View how beam search decoding works, in detail!
Generate detailed image captions
Reconstruct images from masked geospatial data
Convert Hugging Face models for local use
Qwen2.5のチャットボットです。
Search Wikipedia and summarize results
Generate text based on image and question
qwen2.5 0.5bチャットボット。
Explore various AI functionalities in TransformersJS Playground
Train and generate text using a fine-tuned GPT-2 model
Describe images using questions
Compare Open LLM Leaderboard results
Try out my latest and greatest model
Runs Qwen2.5-Math-7B-Instruct-GGUF
Generate text from audio recordings
Manage and analyze text data
Generate text based on your input
Chat with Pixtral 12B Multimodal using Mistral Inference
Quickest way to test naive RAG run with AutoRAG.
Generate YAML config for model slicing
Process and analyze text, images, audio, and video with GPT-4
Generate text based on chat history
llm-jpとチャット。
Zephyr beta
Run user-defined code
Search PDFs for relevant pages using text queries
chatbot specifically designed for students aged 6 and above
Pythia chatbotです。
flux sneller
Analyze document layout from images
Qwen会話
Analyze Japanese text to detect emotions
Execute code snippets and get results
Describe images with detailed questions
A unified multimodal understanding and generation model.
Refine your prompts
Your Personal Prompt Tutor
Generate Python code based on user requests
Granite 3 on device Instruct Model by IBM
Compact LLM Battle Arena: Frugal AI Face-Off!
Explore LLM performance with a leaderboard
Explore and submit LLM benchmarks
Beril7モデルっとチャットしよう!
hjghh
A Fully Open Multilingual Multimodal LLM for 39 Languages
Montチャット。
Interact with the Aya family of models.
View, edit, test and submit Chat Templates
Interact with a chatbot using text and audio
Upload a photo and chat with it using Gemini.
Calculate GPU requirements for running LLMs
Convert handwritten images to text and video outputs
Run SQL evaluation with model inference
Display DuckDB NSQL leaderboard scores
Generate code and text with Code Llama model
Analyze text to understand its structure and meaning
text2text models for document summarization
An end-to-end (e2e) Voice Language Model by Fish Audio.
Chat with Dolphin, a helpful AI assistant
Playground for NuExtract-v1.5
A Fully Open Multilingual Multimodal LLM for 39 Languages
Chat with a large language model
Bot that scrapes Pubmed
state-of-the-art coding performance with 7 B
Chat with a large language model
Chat with a large language model
Create detailed images from text prompts
Generate images from text prompts
New SOTA smol king by Hugging Face
Talk to Qwen2Audio with Gradio and WebRTC ⚡️
Chat with Mini-Omni 2 - powered by Gradio and WebRTC ⚡️
A blazingly fast and powerful AI chatbot that runs locally.
Using YOLO to detect grape leaf disease
A Foundation Action Model For Generalist GUI Agents
The latest version of Ichigo v0.4
Chat with Emma's Genie to get answers and assistance
Chat llama-cpp-agent that can search the web.
Generate code for applications
Generate a leaderboard of models based on "schizo" rating
Generate text responses to your queries
Huggingface space for JanusFlow-1.3B
Ask questions about images and get detailed answers
Start a chatbot server for text-based interactions
Launch a chatbot with image and text understanding
Recommends Netflix Show/Movie based on description and genre
.
Rescuer of Stolen Bikes Program. Stories of Hope & Justice
Leaderboard showcasing Turkish MMLU dataset results.
Insect recognition
Moroccan Arabic Chatbot
Hunyuan-Large模型体验
Talk to Fixie.ai's Ultravox with WebRTC ⚡️
Create 3D mesh by chatting.
Estimate physical properties merely from pouring sound!
Ask all your astronomy-related questions!
Generate Gradio app code from descriptions
Create interactive HTML web pages with your voice
Vote on AI responses to rank models
Generate text descriptions from images
Deploying the Document Q&A Applications with Docker
Controlling Computers with Small Models
Explore and compare LLM models with interactive filters and visualizations
Visual Retrieval with ColPali and Vespa
Chat with a supportive AI psychologist using text or voice
Generate code snippets based on user input
View Chatbot Arena ELO of top models increasing
Generate responses to video or image inputs
VocabSova builds English-langauge lessons and resources.
Chat about images with text input
Create videos with FFMPEG + Qwen2.5-Coder
Generate text responses using conversational AI models
Uses pose estimation to determine what are you touching.
Check if user prompts are on-topic for a given system prompt
Ask questions about images and get answers
Generate text from images and queries
A powerful AI chatbot that runs locally in your browser
QwQ-32B-Preview
Segment and extract subjects from images
Generate structured GitHub issues
Smart Dog Breed Detection, Comparison, and Matching Tool
Chat with Qwen2
Expands (stuffs) flux prompts
powered by the LLaMA.cpp backend
Chatbot
Chatbot
Chatbot
Find Anything in 3D: Open-World 3D Part Segmentation Model
Generate characters complete with world, backstory, and imgs
Generate clickable coordinates on a screenshot
Generate text and images using advanced AI models on CPU
Artistic morphing videos using VQGAN&CLIP
Fast Real-time Object Detection with High-Res Output
Adds Open LLM Leaderboard results to a target modelcard
Chat with Sailor2 for detailed answers in multiple languages
Generate responses to text questions in multiple languages
PaliGemma2 LoRA finetuned on VQAv2
mcp_server & FLUX 4-bit Quantization + Enhanced
Explore how tokenization affects arithmetic in LLMs
Generate code snippets based on user input
Paligemma2 Detection with Supervision
An interactive sketch recognition app built with Gradio, pow
Interact with a multimodal chatbot that analyzes images and text
Generate text responses from images and text input
A model giving fine-grained scores on video quality
A model giving fine-grained scores on video quality
Generate responses by combining text and images
EMNLP 2024
Converse with an AI assistant
Explore and submit LLM benchmarks
Explore and submit LLM benchmarks
Tokenize Arabic text and benchmark tokenizers
Chat with an AI model
HEp2 cell image classifier
Generate summaries for long-form text
Correct grammar in your text
Convert PDF to text using OCR
Say "Hello Llama" and start coding with your voice!
Chat with a helpful AI assistant
Overcome your exam anxiety with practice questions!
GiniGEN Pharm RAG
Explore various text processing tasks with GLiNER HandyLab
Text2Visual Web Converter with AI Image Generation
Generate text using Llama 3.1 405B model
GiniGEN Medi RAG
Mixtral Chatbot with Mermaid Chart Output
Generate Paper Reviews
Talk to Kyutai's moshi - powered by Gradio WebRTC!
Compress text prompts efficiently
A model specialized for generating drug-like structures.
Chat with agents 🤖 and see their thoughts 💭
Talk to the Gradio docs! Powered by Pydantic and WebRTC ⚡️
Generate text and audio responses from voice input
Explore hardware performance for LLMs
Explore and analyze code completion benchmarks
Chat with RakutenAI-7B for answers
Gemini all api here
Build with Qwen
Experiment with Chat Template
Qwen2-VL-2B-Instruct-MNN
Fantasy story generator
Generate text from images using PaliGemma2
Generate human-like text based on user input
Chat with a Russian-speaking AI assistant
Generate interactive web apps with Streamlit
Generate a family tree of a given model
Generate responses to text-based prompts
Generate text responses to user queries
GiniGEN 한글 RAG 법원 판례
Megrez-3B-Omni Chat Demo
NSFW-3B: A Dark, Unrestricted AI Model
Generate text responses using a language model
Qwen2-VL is a vision-language model that performs OCR
Segment anime characters in images
Built with Qwen
Display hardware performance leaderboard
Open LLM(CohereForAI/c4ai-command-r7b-12-2024) and RAG
Analyze SEO of a website
F3-DEMO
Compare responses from Palmyra X 004 and Palmyra Creative
Chat with a language model about any topic
A retrieval system with chatbot integration
text streaming space using Gemma-7B
Classify audio as voice or non-voice
Maya is available in En, Es, Hi, Zh, Ja, Fr, Ru, Ar
Chat with a language model using text input
A Leaderboard that demonstrates LMM reasoning capabilities
Marco-O1 A model similar to OpenAI o1 can reason
Submit and view model evaluations
Submit and view model evaluation results
Generate text responses in a chat interface
Search, load and play with transformer pipelines
QwQ-32B-Preview with Vision 👁
Chat with Komodo Models 🦎
Chat with FastLlama Models 🦙
Generate and customize your story
Generate detailed depth maps from iPhone captures
Test sample model
Generate interactive Jupyter notebooks with user input
Analyze images to generate descriptive prompts
nanonets ocr2 / olmocr / qwen2vl ocr / aya vision / rolmocr
Generate text based on prompts
Generate text based on prompts
?
Text-to-UI - Thanks to Pietro Schirano for the Repository!
stock analysis
Search and summarize web content
Plan your next vacation with the help of an AI!
Chat with a bilingual AI assistant
Browse and search HREF leaderboard data
Chat: llama cpp agent
Chat with ZEUS!
Ask questions about Wikipedia articles in Japanese
Generate detailed chain-of-thoughts for answers
Generate detailed thoughts and answers
Display a loading spinner while preparing space
Compass Academic Leaderboard
A bot that knows a lot about Pokemons
Generate text summaries from PDFs using various models
SolidityBench Leaderboard
This is the project for arxiv pdf summarization
Generate app code from ideas
Track, rank and evaluate open Arabic LLMs and chatbots
TinyLLM-LeaderBoard
An LLM-Powered Calculator that Roasts you
AI driven VTuber & Companion, supports Live2D and VRM.
dataset builder based on teknium's sharegpt-builder
Compare strong zero-shot image classification models
Compare strong zero-shot image classification models
Translate text between multiple languages
Phidata Multimodal AI Agent
Classify images of top Shounen anime protagonists
LLM service based on Search and Vector enhanced retrieval
Generate text and images from prompts
Fact checking baseline. Dense retrieval + textual entailment
Vision Transformer Attention Visualization
Submit and evaluate models on GAIA leaderboard
Chat with Applio for various questions
Generate detailed medical advice from text input
Create 3D models by chatting
Hands-Free AI Voice Chat with a Retro Vibe
Hands-Free AI Voice Chat with a Retro Vibe
Hands-Free AI Voice Chat with a Retro Vibe
Generate embeddings and rerank text or images
🧠Deep🐍Research🌐Evaluator for Long Horizon Learning Tasks
A chat demonstration of MasherAI v6.1 7B!
A chat demonstration of MasherAI v6 7B!
Tiny reasoning model fine-tuned from Qwen2.5-3B-Instruct
Extract text from images or PDFs into Markdown
Display LMArena Leaderboard
AI service generating protein structures from user text
Now supports inference providers and multimodal. No GPU req.
Render 3D graphics using WebGPU
Explore MMBench Leaderboard data
Qwen 0.5B but QwQ
Chat
Gaze detection using Moondream
Create a knowledge graph from text input
Generative Tasks Evaluation of Arabic LLMs
Display a loading spinner with theme settings
Transform research papers and mathematical concepts into stu
Microsoft's iconic Phi-4 model
best foundation model for its size !
Chat with an AI about heart health
Segment subjects in anime images
Gaze Target Estimation
Communicate with an AI assistant and convert text to speech
a tiny vision language model
Detect and estimate human poses in images and videos
Compare uploaded image with Genshin Impact dataset
한글과 멀티LLM 및 RAG 지원
Answer questions using academic papers
2
Display and filter leaderboard data for language models
Electrical Device Feedback Sentiment Classifier
Chatbot
Small and powerful reasoning LLM that runs in your browser
Explore and filter model leaderboard data
Dense Grounded Understanding of Images and Videos
.
Chatbot
Generate images from text prompts
Generate text based on user prompts
Aligns the tokens of two sentences
Redirection to ggml-org collection
GIFT-Eval: A Benchmark for General Time Series Forecasting
Embedding Leaderboard
Generate conversational responses in multiple languages
Multimodal retrieval using llamaindex/vdr-2b-multi-v1
Generate code from images and text prompts
Evaluate language models on AfriMMLU dataset
A french-speaking LLM trained with open data
Find matching images based on input criteria
DABstep Reasoning Benchmark Leaderboard
Generate responses to text and images in a chat interface
Generate responses to text and images in a chat interface
Type an idea, get related quotes from historic figures
Chat with an Italian Small Model
Generic YOLO Models Trained on COCO
Demo for handwritten text recognition model.
Advanced AI chatbot
Get a mystical Tarot card reading
EveryChat RAG
Deduplicate HuggingFace datasets in seconds
Classify text into categories without training
A simple chat bot using Jamba
Chemical Genesis
Any timm model with the transformers integration
Upload PDFs, extract data, and chat about them
Plan ski touring routes with AI assistance
KoboldCpp is a textgen, image gen and more all in one
Convert text to QR code
AI-Powered Research Impact Predictor
This is open-o1 demo with improved system prompt
Generate detailed scientific responses
Chat with LLMs
Generate images depicting President Yoon with prompts
use the ESM3 model to predict protein structures
vector search hf datasets w/ static-retrieval-mrl-en-v1
A quick (but very slow) way to try out bellman in llama.cpp.
Chatbot using New model Jamba(mamba+transformer)
Food classifier
Generate text responses to user queries
Chatgpt but free
Built with Qwen
Display and filter LLM benchmark data
Calculate transformers number of parameters
Submit code models for evaluation and view leaderboard
Generate responses using a friendly chatbot
Find click coordinates on images based on instructions
Explore and submit LLM benchmarks
Implies scanning the market to spot Earning opportunities
Display CompassArena platform
Generate descriptions from images and text prompts
Interact with a Vietnamese multimodal AI assistant
Find answers by describing images
summarize arixv papers and chat with your data
Summarize arxiv papers and chat with your data
Analyze story similarity and metrics like likes, comments, and shares
Create stunning graphic novels effortlessly with AI
Create stunning graphic novels effortlessly with AI
Create stunning graphic novels effortlessly with AI
Create stunning graphic novels effortlessly with AI
Chat with Gemini 2.5 to get detailed responses
Generate detailed character descriptions based on user prompts
Next-generation reasoning model that runs locally in-browser
Chat with a friendly AI assistant
Interact with a helpful AI chatbot
Fast Real-time Object Detection & Tracking with High-Res Out
Ask, Search, and Hear AI answers
Explore and compare open-source large language models
Upload documents and ask questions
Deepseek AI's Janus-Pro-7B: Generate image from text
In-browser unified multimodal understanding and generation.
A unified multimodal understanding and generation model.
Chat with an AI assistant
Translate Japanese text to English
YOLO-based Person Detection
Face detection By YOLO
Chat with a powerful AI model
A quiz app for rows of a dataset
API aggregation & DeepSeek-R1-Qwen-7B gradio demo
chat with phi-4-deepseek-R1K-RL-EZO with CPU
An example using gradient boosting algo from scikit
[Keep updating]Collect everything about o1 and r1!
You can try MedIT Solutions latest release of SUN 2.5B Llama
A short performance comparison
Generate a bullet-point summary from a PDF
Generate customized eLuvLetter config
Zero Shot voice cloning with llasa 3b (Unofficial Demo)
HF Space with Zurich 12B GCv2 5m
HF Space with Zurich 7B GCv2 5m
HF Space with Zurich 14B GCv2 5m
Chat with Dark-Hermes, a helpful AI assistant
A unified multimodal understanding and generation model.
Demo Playground for Florence 2 MSFT
DeepSeek download stats
HF Space with Zurich 1.5B GCv2 5m
Generate detailed stories in various styles
Ask questions, get answers with web sources
Manage and view curated AI tools and favorites
Elegant Janus Multimodal & T2I Demo
Formal reasoning model that can reason and prove theorems
Orchestrator collaborates with multiple agents to write code
Turkish Morphological Tokenizer
OpenAI's Deep Research, but open
Generate uncensored AI responses
YOLO Demo for Manga109 Dataset
Generate responses using images and text input
This is a text-to-speech and translator app.
customizable ChatBot API + UI
Advanced AI chatbot
Generate customized speech from text using a reference audio
Create stunning graphic novels effortlessly with AI
A leaderboard to rank large reasoning models
Space for LM similarity on Open LLM Leaderboard data
Run customizable scripts from environment variables
innovation global recipes with health and personalized
Analyze datasets with natural language prompts
Implies scanning the market to spot Earning opportunities
Process and extract data from PDF documents
Deepseek Multimodal -Automated Real Anything-to-Anything
image captioning, VQA
Chat with an image-aware assistant
The only leaderboard you will require for your RAG needs 🏆
Generate images from text descriptions
Write musical scores with LLaMA
Browse tools and agents to use in smolagents
Granite Text & Vision Chatbot
Generate medical advice based on symptoms
Philosopher AI - Exploring the Depths of Ethical Reasoning
Ranking of LLMs for agentic tasks
Latest text-generation model by META - Meta Llama3.1 8b
Latest text-generation model by META - Meta Llama3 8b.
Chat with a friendly AI assistant
Chat with a friendly AI assistant
Joke Generator using a a rest API
M-RewardBench Leaderboard
NQLSG Qwen2.5 14B MegaFusion v9.3 Playground
Experiment with and compare different tokenizers
DeepSeek R1 Distill Qwen 1.5B Demo GGUF(Q8) Fully in CPU
AI-Powered Research Impact Predictor v2
OpenAI's Deep Research, but open without api key
OpenAI's Deep Research, but open with Groq(rate-limited)
Perform SQL against a database using plain English input
Upload data to evaluate with Selene models
See, read, and reason—better together.
OmniParser, turn your LLM into GUI agent
Run GGUF directly on your browser!
Chat with Reflection-L3.2-JametMiniMix!
Online demo of paper: Chain of Ideas: Revolutionizing Resear
Upload a video or image to get conversational explanations
Chatting with scientific papers made easy
cosmos reason1 / docscopeocr / visionocr / captioner relaxed
Chat with Napoléon models 🦅
Generate text based on prompts
Generate text based on prompts
Embed and interact with a Gradio app
Chat with a virtual assistant
Generate essays on any topic in multiple languages
Generate responses to user messages in a chat interface
Chat with a helpful AI assistant
Generate UI code snippets from descriptions
Generate UI from text prompts
Generate detailed responses using a mixture of AI agents
Generate text and segment images using PaliGemma 2
U-MATH and μ-MATH leaderboard
Text2Visual Web Converter with AI Image Generation
The ultimate guide to training LLM on large GPU Clusters
Mark regions in images based on text descriptions
Generate video highlights from uploaded video
sign in to receive news on the iPhone app
Generate answers by combining text and images
Generate video highlights and playlist
Ask questions about your PDF
Llama 3.2 - SambaNova API
Llama 3.2 - SambaNova API (Gradio)
Simple CHAT UI to test HF Models via your HF API
Small model can do big things.
Llasa-1B-Multilingual finetuned using simon3000/genshin-voic
A tool to detect facial expressions
Compare SigLIP1 and SigLIP2 on zero shot classification
Generate text in character based on user input
multilingual-e5-largeを使ったタグ検索
Detect objects in images and videos
Try latest FluentlyLM model!
Support by Parquet, CSV, Jsonl, XLS
Chat: exllama v2
Video Anomaly Understanding.
Recognize Bangla handwritten words from images
A Generalist Diffusion Model for Vision Perception
Generate images from text descriptions
Display and analyze reward model evaluation results
Generate depth maps from images
Find personalized scholarship recommendations tailored to your profile
Space demoing Phi4 MultiModal
FastRTC Voice Agent with smolagents
A leaderboard for LLMs powering smolagents
Chat with Microsoft's phi-4 or phi-4-mini models
Large Language Diffusion Models
Good Arabic Model
Classify unstructured comment text.
Generate creative radio Ads with AI.
Have a video chat with Gemini - it can see you ⚡️
Chat with AI and upload files for context
Ask questions and get detailed answers with web search support
OpenAI's Deep Research, but open
@image @rAgent @web @text @tts1 @tts2
Retrieve transcripts from YouTube videos with various format
Insanely scale your finetuning data 😱!
Multilingual ChatBot for SEA Languages
Deepsex14B
Generate text responses to your queries
Let Us Detect your hallucinations! Demo for our framework.
Detect hallucinations in answers based on context
Automatice License/Number Plate Recognition
Identify Korean grammar issues in mixed-language texts
Convert handwritten notes to digital format using AI
A guide through immersive text-based adventures
Create an AI agent using Hugging Face Spaces
keval space
Extract and visualize knowledge graphs from text
Chat with a healthcare AI assistant
Translate text between English and other languages
SFT Tiny Titans Agentic RAG Party w Torch, Transformers
Generate text responses in a chat format
State-of-the-art Indic language translation by AI4Bharat
Identify the best matching label for an image
Chat with Gemma 3 about images
Extra Search tool(google-custom,brave,priority) examples
Powered by VIDraft
Live Interactive demo for EMOVA with Qwen-2.5 backbone
Generate responses to text prompts in a chat interface
Ask questions about cosmetics and get tailored responses
Browse one million chatbot conversations from lmsys-chat-1m
Chat with multimodal gemma-3-12b-it or gemma-3-4b-it models
Convert images and text to structured documents
Rag example with Gemma3-4B and Smolagents
Rag example with Qwen2.5-0.5B-Rag-Thinking +
English version of the blog post introducing FAT5 model
CLIP embeddings for both text and image similarity search
Segment objects in images using text prompts or scribbles
Anonymize sensitive text locally in your browser
MIPA(Korea Mobile Infra Promotion Associaton)
Interact with Qwen2.5-VL-32B-Instruct for text and image/video responses
Explore and submit unlearning results for LLMs
Deepseek v3-0324 + Real Time Deep Research
hunyuan-turbos模型体验
Hunyuan T1模型体验
Deepseek v3-0324 + Real Time Deep Research
Generate text and speech from text, audio, images, and videos
Reasoning + Deep Research + API(NVIDIA H100 GPU)
Generate detailed text responses based on prompts
Ask questions and get expert answers from AI models
Compare responses from selected huggingface models
Refine uploaded paper by selecting text and specifying needs
Compass Academic Leaderboard Full Version
Generate text descriptions from images and prompts
Display and explore a leaderboard for model evaluations
Assistente que ajuda a encontrar script SQL
Detect Toxicity and Categorize them using BERT based model
OmniParser, turn your LLM into GUI agent
Llama-4-Maverick-17B + Real Time Deep Research
View detailed model outputs for specific benchmarks
Display a web page
Open Persian LLM Leaderboard
Compare model answers to questions
HF Space for Mistral-Small-24B-Instruct-2501 running on Zero
State-of-the-art open-vocabulary image segmentation ⚡️
Compare two images for similarity
Finetuning_Multimodal_LLM Phi3
multimodal,search,image capabilities on par with GPT-4o
Generate text with a deep learning model
Generate bilingual chat responses
Generate throughput plot for LLMs on devices
Ask questions and get informed answers
Fire and Smoke Detection
Generate a video visualizing how a model attends to an image while generating text
Chat with images and get detailed responses
Chat with images and text
Chat with an image-aware assistant
Chat with model about images
Model trained using AZ Service documents
Complete list of past Daily Papers
you to experience how Multilingual tokenizers work.
Your AI Agent for Academic Research
Chatbot arena for software engineering tasks
thought that reasoning into LLMs without modification
BAIDU's LLM, https://yiyan.baidu.com/
Chat with an AI and track energy use
Display a React app with TypeScript
Extract text from images in multiple languages
Free AI blog generator using GPT-4.1 with search, file,image
Diagnose eye diseases and visualize model explanations
1.58 Bits Native Micro LLM from Microsoft
Object Detection & Scene Understanding for Images and Video
Palmvein Recognition Demo
Describe images and answer questions about them
Generate website code from descriptions
Generate responses to text prompts in a chat interface
A hybrid reasoning model that runs locally in your browser.
Generate any application with Qwen
Play an interactive game with AI character "糖糖"
Chat with characters from 50 Chinese novels
Generate text using EvaByte, novel byte level language model
Describe masked parts of images
Chat with Microsoft's phi 4 reasoning plus
Generate lecture materials and audio using AI
Private-BitSix-Mistral-Small-3.1-24B-Instruct-2503
qwen3-30b-a3b-research + Real Time Deep Research
qwen3-235b-a22b-research + Real Time Deep Research
Chain-of-Recursive-Thoughts TEST
Multi-agent AI assistant for finance, news, and analysis.
Interact with an AI agent to perform web tasks
Seed1.5-VL API Demo
NextGen Evaluation Benchmark and Leaderboard for Arabic LLMs
A Unified Evaluation of LLMs for RTL Generation.
Convert image text to Markdown
Ilúvatar - Creative Design & Invention AI
Generate images, check orientation, apply sepia filter, and find prime factors
Browse curated AI applications
Turn a screenshot into a static page with HMTL / CSS
Universal-Scene Text Recognition Model with High-Accuracy
Korea
predicted prices inferred by applying Vidraft's models
Start camera to get descriptions based on instructions
Chat with Falcon-H1 models
Next-Gen High-Precision Doc Parsing Solution
Cognitive layer for enhanced reasoning with Gemma-27b
A VLM-based message decoder that is trained via GRPO
Radiology Image & Report Explainer Demo. Built with MedGemma
Yet another WebGPU based SmolVLM, re-implemented in Vue
YOLO12 Demo for Dataset AnimeText
Interact with a DMind AI Assistant for Web3 insights
Educational Content Creator Assistant
Demo for MMaDA: Multimodal Large Diffusion Language Models
Generate descriptions of objects in real-time video
Thorax-reading AI model trained on top of Florence2-Large
Chat: recetas en español
UniVG-R1 demo
HuggingChat --> Flutter --> Apk
Scrape web/GitHub for RAG-ready datasets.
Generate optimized code for image generation tasks
Compare Vision Language Models
Detect objects in images and get labeled results
Intelligent conversations with precision focus
MCP Server to check website stats via Plausible Stats API.
CPU-only Zero-Shot Text Classification
Enhance LLMs with strategic tool use for math problems
Select elements in images using text instructions
This space defines a RAG MCP server
Web Localization powered by Holo1
Display leaderboard and analyze samples
Short-Story Generator
This is FACTS Grounding Leaderboard, but for Open LLMs!
Chart GPT' AI-Powered Multi Diagram and FLUX Image Generator
Convert Free Text Into Json Using AI
Generate conversational responses based on chat history
Chat with an AI assistant using text and images
Reasoning + Multimodal + VLM + Deep Research + Agent
Multilingual Text Embedding Model Pruner
Submit model evaluations and view leaderboard results
Display OCRBench leaderboard with model scores
Demo for Nanonets-OCR
Dolphin Demo
voice-trans
Live Interactive demo for RACRO-7B-CRO-GRPO backbone
EfficientVLM
Generate code from text prompts
AI generates PPT with diagrams and images from given topics
nanonets ocr / smoldocling / monkey ocr / typhoon ocr
https://nanonets.com/research/nanonets-ocr-s/
Analyze dental X-rays to detect objects
Generate cute AI conversations and save them
Describe moble UI screens to enable AI agentic capabilities
Chat with Microsoft's 1.58bit Bitnet model!
Generate a story from up to 10 images
A fun way to search the internet
A sophisticated AI-powered knowledge retrieval and analysis
LightGlue demo
Translate text between 100 languages
Extract text from images and XML files using OCR models
View leaderboard of LLMs on EQ-Bench
Organized AI — the essential first stage of AGI
Analyze images, videos, and audio to generate detailed responses
demo
OCR, VQA, Thinking and Object Detection.
Generate text from images, videos, and audio
ServiceNow-AI model chat
Visual Audio Question Answering
DNA Diffusion
THUDM/GLM-4.1V-9B-Thinking Demo
Explore object detection, visual grounding, keypoint Detecti
Visual Question Answering - Autonomous Driving - SmolVLM2
Chat with an AI that shows its thinking process
A lightweight version of DeepGit
Customer Churn Decision Tree Model
Official Space for SpatialTrackerV2
Neural network demo for customer purchase prediction
Unified MLLM with Text-Aligned Representations
State-of-the-art Zero-shot Object Detection
Use hugging face's new smollm3
demo to test classifier/scorer attempts
Qwen Image LoRA's
Use LLM to generate a knowledge graph from your input data.
How Language Models Turn Text into Meaning, From Traditional
Real-time video captioning powered by FastVLM
Kimi models
An interactive simulator for strategic business competition.
Real-time video captioning & Object Detect
Chat with a compact language model for high-quality responses
AGI(Artificial General Intelligence)
valuating Human-Level Novel Creation Capability
Analyze academic paper layouts from images
Translate your text, audio, image from English to Ukrainian
Generate Lightroom presets from images and prompts
Multimodal ViT for skin cancer diagnosis
Search audio for relevant chunks
Identify AI-generated images from real ones
Chat with advanced language models
Visualize accuracy curves for video models
Translate text between multiple languages
Generate web application code from descriptions
Interact with a chatbot using text and images/videos
Visualizing model responses to companionship prompts
INTIMA Benchmark - Model Responses Explorer
Extract and visualize layout from PDFs or images
valuating Human-Level Novel Creation Capability
Generate text responses to your queries
OpenAI gpt-oss-120b and gpt-oss-20b Chatbot
Chat with OpenAI's gpt-oss-20b model
In-browser tool calling, powered by Transformers.js
Chat with a roleplaying AI assistant
Experiment with the Tiny VLMs here
Generate detailed responses to text prompts
Reasoning model specialized for OCR/Markdown generation.
Zero Shot Object Detection
Segment any objects and track them through a video with SAM2
AGI(Artificial General Intelligence) based Webtoon Generator
Chat with Gemma 3 270m IT
Generate DNA sequences and visualize 3D structures
A demo for the IntrinSight-4B
Display model performance leaderboard
The official demo of MangaLMM
Extract text and highlight from manga panels
Scaling Omni LLMs to Personalized Long-Horizon Speech
Information about Goa
AI companionship leaderboard based on the INTIMA benchmark
Konkani LLM with Gemma 3
In-browser video tracking, powered by Transformers.js
Classification with Random Forest, LightGBM and XGBoost.
Nascent conscious A.I
AGI(Artificial General Intelligence)
Visualize rich, dense image features locally in your browser
Generate a fictional story from an image
Get an outfit idea for your Reachy Mini
VITA-1.5 demo
Run code and analyze data in a Jupyter notebook
we present a lightweight classifier one head two modal
Explore the Konkani and English Bible
Compare art image predictions with ground truth labels
Smollm3 for French Understanding
Generate answers from images and text
Chat with K2-Think to get answers and assistance
Vision-Language Models for Document Conversion
Chat with Darwin-Qwen3-4B evolutionary merged model
Compress and reconstruct text into semantic embeddings
AI that predicts stock moves from news and explains why
demo of l-operator with no commands
UniGenBench: a unified T2I generation benchmark.
ChatGPT with real-time web search & URL reading capability
Gemma 3 (270M) run on Ollama using a single-core CPU only
Chat with an AI assistant using text and images
Explore sentiment trends and stock prices for tech companies
Convert old Russian text to modern orthography
Vibe Coder 20B chatbot
for document parsing task
Compare two AI models by sending them code and seeing their responses
Interact with a multimodal AI assistant using text, audio, images, or video
Interactive timeline to explore the 🤗Transformers models
Human vs. AI: Super-Resolution Battle
Chat using Qwen3-VL for Image, Video, PDF, and GIF
Generate text responses to chat prompts
Recognize text and elements in images
Classify waste images to get recycling tips
A Tokenizers Leaderboard and a space to do token analysis.
Generate Shakespearean text using a diffusion model
Run generative inference on images to reveal perceptual effects
nanonets2 / dots.ocr / olmOCR2 / chandraOCR
RuQualBench Leaderboard
Florence-2 vision models demo. (transformers)