AI projects from Hugging Face

MiniCPM-OCR vs Unlimited-OCR-2

nielsr · Kit

Reads a document page with two OCR models and shows their results next to each other, with the detected regions linked to each text block. It suits people choo…

Mage-VL-Cowork Computer Use

nielsr · Kit

Lets you give a task to the Mage-VL-Cowork model and watch it click, type, scroll and use a terminal on a disposable Linux desktop. It suits developers studyin…

RealESRGAN Pytorch

Nick088 · Kit

Upscales images and videos with Real-ESRGAN through a friendly Gradio app. It suits photographers, video editors and creators who want sharper, larger versions…

AUDIO

NguyenVanMau2311 · Kit

Runs a small Node.js style project in a Docker container on port 7860 under the name AUDIO. The source does not say what its audio features are, so it suits de…

Remove Silence From Audio

NeuralFalcon · Kit

Cuts the silent stretches out of an audio recording in a small Gradio app that runs on basic CPU hardware. It suits podcasters, editors and anyone tidying spok…

HiDream Unlimited

namelessai · Kit

Makes images with HiDream from a Gradio web page. The README says you can create as many as you like, and lists no settings.

VoxPocket Khmer TTS

muyleanging · Kit

Turns Khmer text into speech in the browser, with voice cloning from a short clip, optional styles and voice design from a description. For creators and resear…

MTEB-BR Leaderboard

MTEB-BR · Kit

Ranks text embedding models on native Brazilian Portuguese tasks, with 93 models scored on 22 tasks. A static leaderboard page for researchers and engineers ch…

Open Universal Arabic Asr Leaderboard

msalhab96 · Kit

Compares open-source speech recognition models on Arabic across several dialects, in a Gradio page. For researchers and developers choosing an Arabic speech-to…

ZONOS3 Mini by mrfakename

mrfakename · Kit

Turns text into speech in ten languages with the ZONOS3-Mini model, with 27 preset voices, voice cloning from a short clip, rate and loudness controls and mood…

Confucius4-R2T2 WebGPU

mrfakename · Kit

Turns Chinese and English speech into text inside your browser on WebGPU, from audio files or a live microphone. It suits people who want transcripts without s…

Wasm Agents Blueprint

mozilla-ai · Kit

A static web page from mozilla-ai for testing AI agents powered by WebAssembly, naming the Devstral-Small-2507 and Qwen3-8B models. It suits developers explori…

Spark-X2.6-1.7B WebGPU

mohdmahmodi · Kit

Runs the Spark-X2.6-1.7B chat model inside your browser on WebGPU, so what you type stays on your device. It suits people with desktop Chrome or Edge who want…

Arabic Auto Tashkeel

MohamedRashad · Kit

Adds tashkeel, the Arabic vowel marks, to plain Arabic text through a Gradio app. It suits teachers, learners and speech developers who need marked text.

OmniVoice MLX

mlx-community · Kit

Speaks text with the OmniVoice text-to-speech model through the community MLX backend, for people who want to try it or run it on an Apple silicon Mac.

StatePact Concurrency Playground

Mithun-2714 · Kit

Simulates how agents that share mutable state collide, under five isolation modes, in your browser, so you can watch overselling, lost updates and write skew.

Teacher in the Loop

MithrilMan · Kit

Runs small 8M-parameter text-to-speech voices distilled from Kokoro-82M entirely in your browser, with audio samples that compare the training recipes.

Reachy Mini ElevenLabs Conversation

mindmodelai · Kit

Lets a Reachy Mini robot hold spoken conversations through an ElevenLabs Conversational AI agent, with head movements and lip sync, for owners of the robot.

YourMT3

mimbres · Kit

Runs the YourMT3 demo in a Gradio app. Its folder names point to turning audio into MIDI music transcription, and it suits people who work with music and audio…

Grounding DINO Demo

merve · Kit

Finds objects in a picture from a text description, with no fixed list of labels. A Gradio demo of the Grounding DINO open-set detector, for developers and vis…

ChatGPT Prompt Generator

merve · Kit

Generates ChatGPT-style prompts from a short starting phrase, using models trained on a public prompt collection. Suits anyone who wants ideas for what to ask…

Z Image Turbo by Maynor996

Maynor996 · Kit

Generates images from text prompts with the Z-Image-Turbo model, in a Gradio page that runs on ZeroGPU. Deployed by Maynor996 with the same interface as the or…

Sana Manga Coloring

masterofaudio2077 · Kit

Colors black-and-white manga pages with two Sana 600M models, one that adds color on top and one that repaints the whole page, for artists and fans working on…

Music Stem Transcriber

mankalakiot · Kit

Runs a small Gradio app, in the browser or on your own computer, that its name says transcribes music stems. The source gives no description, so the exact inpu…

A Universe Named

Manii77 · Kit

Reads a movie review and judges its sentiment with a DistilBERT model, for people who want a quick, automatic read on how a review feels.

Gradio Lipsync Wav2lip

manavisrani07 · Kit

Runs Wav2Lip lip syncing in a Gradio page, which matches mouth movements to speech audio, for people who experiment with video and voice tools.

Image Face Upscale Restoration by malekradwan130

malekradwan130 · Kit

Upscales images and restores faces in them, for people who want sharper pictures of people. Its title lists GFPGAN, RestoreFormerPlusPlus and CodeFormer.

Fine T2i Api

ma-xu · Kit

A Docker packaged Python app tied to the fine-t2i dataset, whose address names it as a way to explore that data. The README gives no description, so its exact…

TranskunGUI

Lollikit · Kit

Gives the Transkun piano transcription model a simple Gradio screen, so you can turn a piano recording into notes in the browser. Built for musicians, students…

GPT OSS 20B Heretic Chat

locojefe · Kit

Lets you talk to the gpt-oss-20b-heretic language model in your browser. It runs on ZeroGPU and shows only the final answer, for people who want to try this co…

VideoLLaMA2

lixin4ever · Kit

A chat app for understanding media such as video, built on the VideoLLaMA2 models. Runs in the browser as a Gradio app on ZeroGPU, for people who want to ask q…

LightOnOCR-3 Demo

lightonai · Kit

Reads a page image and returns its text as Markdown, with layout grounding. A demo of the LightOnOCR-3 models that runs in the browser on ZeroGPU.

Project Homunculus URDF viewer

lerobot · Kit

Shows a data glove over an animated 3D hand in the browser, with sliders for 16 joints and a USB glove mode that reads live finger sensors. Runs with no backen…

Pose Skeleton Multi-Orang (DWPose/RTMW)

kulkas2pintu · Kit

Turns a photo into an OpenPose-style pose map, built to handle several overlapping people in one frame. The maps work as control images for ControlNet pose mod…

Falcon1 2.6M Image

Kuantum-ai1 · Kit

Hosts a Gradio demo of the Falcon1-2.6M-Image model. The README gives no description, so the name is the only hint that it works with images.

Anime Recommendation System

krishnaveni76 · Kit

Recommends anime from your tastes or a title you liked, using collaborative, content-based and popularity-based methods. A Streamlit app for anime fans and for…

Duyu-small

KaanAydinli · Kit

Transcribes Turkish and English speech inside your browser from a recording or an uploaded file. A small model runs on your own device, so your audio stays on…

Laplace-1-Vector

JuneoAI · Kit

Scores the options an agent could take, or predicts what happens next, before the action runs. A demo and MCP server for the 4B Laplace-1-Vector decision model…

Transcripción automatica en aragonés

Juanpabl · Kit

Transcribes Aragonese speech to text from an uploaded audio file or a microphone recording of up to 60 seconds. A demo of an Omnilingual LLM-3B model fine-tune…

Finetune

josephwong135 · Kit

Packages Hugging Face's AutoTrain, a no-code way to train AI models, as a Docker app. For people who want to train a model without writing code, in a browser o…

DFlowNovo De Novo Peptide Sequencing

joelinator · Kit

Predicts peptide sequences from tandem mass spectrometry files with a flow matching model, returning calculated masses and confidence scores, with results you…

Rein-NPC playground

jmc0 · Kit

Lets you talk to three game characters in a small town, played by a 4B model that downloads once and runs in your browser, with the model's decisions shown und…

humanizer

jialinyyzz · Kit

Rewrites AI-written drafts in English or Chinese so the text sounds human, keeping figures, dates, names and quotations as they are, with a way to lock chosen…

Image Face Upscale Restoration by jhon19792025

jhon19792025 · Kit

Restores and enlarges faces in photos, with several restoration models offered in one Gradio page. For people repairing old or blurry portraits. Use only photo…

Basal-1.5 Demo & API

jglowa · Kit

A Gradio demo and API for the basal-1.5 models by Remek Kinas, in three variants named 4.5B, max and mini, online or on your computer with Python 3.12.

Qwenputer Front Panel

jgalego · Kit

Replays recorded runs of Qwenputer, a Qwen3.5-4B model with a RISC-V CPU built into extra layers, beside a front panel of layers, registers and RAM. It runs in…

ANCHOR: the page changed, which robot noticed?

isntlucxs · Kit

Shows a traditional RPA script and the ANCHOR automation agent running on the same web page before and after it changes, at five levels of change, in your brow…

NTv3 Foundation Models for Genomics

InstaDeepAI · Kit

Introduces InstaDeepAI's NTv3 genomic foundation models, which read up to 1 Mb of DNA, and points to runnable PyTorch notebooks, in a browser page you can also…

FM4M-demo1

ibm-research · Kit

A Gradio demo from IBM Research that names three IBM materials models, smi-ted, selfies-ted and mhg-ged. For researchers and developers who want to look at how…

Granite Vision Document Intelligence

ibm-granite · Kit

Pulls summaries, CSV data, code, tables and image descriptions out of PDFs and images, using IBM Granite Vision and Docling in a Gradio demo.