AI projects from Hugging Face

Omni Video Factory by FrameAI4687

FrameAI4687 · Kit

Generates video from a text description or a still image and can extend a finished clip, on a Gradio page that runs in the browser. For creators testing AI vid…

KLM 1.5-Chat Preview

Eclipse-Senpai · Kit

Chats with a small 99M-parameter language model in the browser, with an optional reasoning mode, a calculator and live web search. It suits people who want to…

Omni Video Factory

vamo455 · Kit

Makes video from text, makes video from an image, and extends an existing clip, on a Gradio page that runs in the browser. For creators who want quick AI video…

OmniVoice

k2-fsa · Kit

Clones a voice and speaks text in it across more than 600 languages, on a Gradio page that runs in the browser. For people who want to try voice cloning text-t…

RUKOPYS Leaderboard

UkrainianCatholicUniversity · Kit

Ranks OCR systems on reading handwritten Ukrainian, scored on whole pages from the RUKOPYS test split. Researchers and model builders can compare runs right in…

Photo Enhancer

MegaPotatoAI · Kit

Restores detail in noisy, soft or heavily compressed photos at the same size or 2x larger, using the MegaPotato model on a static page. Free demo for logged-in…

4K Upscaler

MegaPotatoAI · Kit

Enlarges images to 4K, 8K or 16K with an AI upscaler, shows the exact output size first, and lets you compare a plain resize with the AI result. Free demo for…

Visualize Dataset (v2.0+ latest dataset format)

lerobot · Kit

Browse robotics datasets in the LeRobot format with synchronized video, interactive charts, 3D robot replay and tools to flag bad episodes. For robotics resear…

Hub Stats

huggingface · Kit

Shows growth, downloads, licenses, model trees, trending repos and papers across the Hugging Face Hub as one static page with every number precomputed. For peo…

Kokoro TTS

hexgrad · Kit

Reads text aloud with the compact Kokoro-82M model on a Gradio page that runs in the browser. For people who want to try this text-to-speech model without inst…

Image Upscaler

Phips · Kit

Processes images with a set of Phips models on a Gradio page, with model names that point to JPEG, H264 and noise clean-up. For people who want cleaner, sharpe…

UGI Leaderboard

DontPlanToEnd · Kit

Shows a leaderboard of AI models scored on what its title calls Uncensored General Intelligence, as a page that runs in the browser or in Docker. For people co…

InferenceSupport

huggingface · Kit

Points people to discussions about the Inference Providers feature on the Hugging Face Hub, as a small static page run by Hugging Face. For Hub users who want…

MTEB Leaderboard

mteb · Kit

Ranks embedding models for text, images, audio and video on a leaderboard page that runs in the browser or in Docker. For people choosing which embedding model…

FLUX.2 Klein Multi LoRA V2

M3st3rJ4k3l · Kit

Edits images with FLUX.2 Klein 9B and LoRA add-ons on an experimental Gradio page. For people who want to try image edits in the browser and read how the app i…

VRAM & GPU Cost Calculator

fastgpu · Kit

Estimates how much GPU memory a Hugging Face model needs to run or fine-tune, and shows the cheapest GPU setups with live rental prices. For people planning to…

Microduck Sandbox

pollen-robotics · Kit

Lets you steer a simulated Microduck robot in the browser with trained walking, sitting, rolling and kicking policies, plus a wheeled variant. For robotics and…

Qwen3-TTS Demo

Qwen · Kit

Turns typed text into speech with the Qwen3-TTS models on a Gradio page, in the browser or on your own computer. For anyone who wants to hear the model's voice…

The Ultra-Scale Playbook

nanotron · Kit

Teaches how to train large language models on big GPU clusters, as a web guide you read in the browser with a PDF copy in its files. For engineers and research…

Omni Image Editor

selfit-camera · Kit

Edits images, makes pictures from text, upscales photos and removes watermarks on a Gradio page that runs in the browser. For anyone who wants quick image fixe…

DeepSeek-V4.1-Flash-1017

deepseek-ai · Kit

An image and text model for reasoning, coding and agent tasks with a 1M-token context window, updated from DeepSeek-V4.1-Flash. Made for developers who build a…

DSpine for Qwen3.8-27B

tencent · Kit

A five-layer draft model that guesses 16 tokens in parallel for Qwen3.8-27B, so the large model can check them together. Made for teams that serve that model.

CCORE GLB-3D-Coder

ccore · Kit

Writes a Three.js page from a text prompt that previews a low-poly 3D asset and exports it as GLB for Godot or other editors. Made for game developers and 3D h…

Qwen3.8-27B

Qwen · Kit

Reads text, images and video and replies in text, with a 27B open model tuned for coding, research and multi-step agent work. Suits developers who run models t…

Qwen3.5-4B-3D-Coder

ccore · Kit

Writes code and interactive Three.js 3D scenes from text prompts, and from a reference image when you add the optional vision file. An early preview of a 4B fi…

Arete-27B

NousResearch · Kit

Answers politically sensitive questions with a 27B text model that Nous Research retrained from Qwen3.8-27B to shift its viewpoint. Made for assistant builders…

Ripple-65B Preview

ricursiveAI · Kit

Runs terminal coding agents on a 65B dense language model that reads up to 1,048,576 tokens of context. Made for developers and researchers who want open Apach…

Idol by speridlabs

speridlabs · Kit

Turns one picture of an object into a 3D Gaussian splat, building the hidden sides too. Made for artists, researchers and developers who want a 3D file from a…

QIE-2511 Rapid-AIO LoRAs Fast (Experimental)

aet256 · Kit

Runs a browser demo of Qwen Image Edit LoRAs as a Gradio app on Hugging Face Spaces. The README gives no description, so the page itself shows what it does. Fo…

Qwen 2511 + Flux.2 Klein

AST-1320 · Kit

Edits an image with Qwen and then improves the result with FLUX.2 Klein, in a Gradio app you open in your browser on Hugging Face. The README gives no further…

Harness Leaderboard

joelniklaus · Kit

Compares nine coding agents running the same open model, with three attempts per task, confidence intervals and public trajectories. For developers choosing wh…

MOSS-Image Character & Style Catalog

hide1 · Kit

Browse and search 34,680 generated character and style images, then copy each one's prompt and tags. A read-only viewer for image makers that needs no Python o…

AI Text Humanizer

fendouai · Kit

Strips stock phrases from English and Chinese text in your browser, leaving code, paths, numbers and quoted text alone. For writers who want a cleaner draft wi…

Idol

speridlabs · Kit

Turns one image into a 3D object made of Gaussian splats, in a Gradio demo you run as a Hugging Face Space. For artists and researchers who want to try single-…