Arena Leaderboard
🏆
4.94k
View the LMArena leaderboard in full‑screen
kyzh spaces
-
-
XTTS
🐸2.77kGenerate speech from text using a reference voice
-
Open ASR Leaderboard
🏆1.4kCompare speech‑recognition models by WER and speed
-
List of Demos
😻78Explore and filter demo spaces with customizable view
-
Huggingface Leaderboard
🏆103Explore Hugging Face author rankings and stats
-
Shopify Image Background Replacement
🖼456Replace product image backgrounds with custom scenes
-
ArXiv New ML Datasets
📚21Discover arXiv papers that introduce new datasets
-
Wonder3D
🚀477Generate 3D views from a single image
-
VideoRetalking
⚡334Audio-based Lip Sync for Talking Head Video Editing
-
Face Recognition SDK
🤨167FaceOnLive On-Premise Solution
-
ID Document Recognition SDK
🪪346FaceOnLive On-Premise Solution
-
Whisper Large V3
🤫847Transcribe audio or YouTube videos to text
-
Distil Whisper Web
👀229Transcribe audio files to text instantly
-
StyleTTS 2
🗣732Efficient, fast, and natural text to speech with StyleTTS 2!
-
HierSpeech++ (Zero-shot TTS)
⚡401Generate high-quality speech from text using a prompt audio
-
NIST FRVT TOP 1 Face Recognition, Face Liveness Detection, Face Analysis
🥇600Compare two faces to verify identity
-
OutfitAnyone
🏢2.81kGenerate virtual try‑on images for any model and clothing
-
Marigold Depth Estimation
🏵501Generate depth maps from your photos
-
Singing Voice Conversion
🎼262Transform your voice into a singer's
-
OpenVoice
🤗1.13kGenerate speech in a cloned voice from a short audio clip
-
IP-Adapter-FaceID
🧑1.01kGenerate AI images featuring your own face
-
PASD Magnify
✨246Magnify subject details and enhance image quality
-
Segment Anything Web
💻275Segment objects in images using point prompts
-
Depth Anything
🌖565Generate depth map from a single image
-
InstantID
😻3.62kGenerate personalized images preserving your face identity
-
InstantStyle
👁455Style-Preserving Text-to-Image Generation
-
InstantMesh
📚1.58kCreate a 3D model from an image in 10 seconds!
-
mergekit-gui
🔀290Merge AI models using a YAML configuration file
-
Face to All
👨844AI filter for your portraits
-
Reward Bench Leaderboard
📐431Explore and compare model scores on RewardBench benchmarks
-
OOTDiffusion
🥼1.13kHigh-quality virtual try-on ~ Your cyber fitting room
-
MeloTTS
🗣476Fast, efficient, & multilingual text-to-speech
-
Audio Editing
🎧328Edit audios with text prompts
-
Whisper
📉2.79kTranscribe audio files into text instantly
-
Instant Text-to-3D Mesh Demo
🚀63Generate 3D models from text prompts
-
Remove Video Background
🎞360Easily remove your videos background!
-
Playground V2.5
🌍1.14kGenerate highly aesthetic images
-
TTS Arena V2
🗣966Compare and rank TTS voices by listening and voting
-
Chunk Visualizer
🍫231Pick a text splitter => visualize chunks. Great for RAG.
-
TransferAnything
🐢345Create custom images by transferring layout, color, and style
-
LoRA Studio
🪄618Browse and run thousands of community trained LoRAs
-
Remove Background Web
🖼758In-browser background removal
-
MLLM-guided Image Editing (MGIE)
👩332Edit images using natural‑language instructions
-
BRIA RMBG 1.4
💻880Remove background from images instantly
-
modelscope-studio
🚀70A third-party component library based on Gradio.
-
YOLO World
🔥490Detect objects in images or videos
-
Depth Anything Web
🖼277Generate depth map from any photo
-
MTEB Leaderboard
📊7.54kEmbedding Leaderboard
-
Whisper Web
🎤1.29kTranscribe audio files to text instantly
-
MusicGen
🎵5.08kGenerate music from a text description and optional melody
-
Real-Time Text-to-Image SDXL Lightning
⚡618Real-Time Image Generation with SDXL Lightning
-
MusicGen Web
🎵254In-browser text-to-music w/ Transformers.js!
-
— AI Jukebox —
🎶411Generate music powered by AI
-
IDM VTON
👕2.12kHigh-fidelity Virtual Try-on
-
— Zero GPU Spaces —
⚡964List of spaces using ZERO-GPU
-
StoryDiffusion
👁617Generate consistent image sequences from text and photos
-
Instant Video
⚡622Fast Text 2 Video Generator
-
StableVITON
👕55Transform your look with virtual try-on
-
GFPGAN
😁1.1kEnhance and restore old photos and AI-generated faces
-
OpenVoiceV2
🤗355Generate speech in a target voice from a short audio clip
-
LLM Performance Leaderboard
🐨468View the LLM leaderboard rankings
-
IC Light
📈1.37kRelight photos with AI using custom lighting prompts
-
3DGen Arena
🐠102Generate and compare 3D models from text or images
-
Parler TTS Expresso
⚡92Convert text to speech with emotion
-
SDXL Flash
⚡320High quality image generation in 3 second
-
CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
🚀190Generate a 3D mesh from a single image
-
AutoQuizzer
🧑226Generate a quiz, play or let 🦙 LLM play
-
Yolov10
📉101Detect objects in images with customizable YOLOv10 models
-
GenAI Arena
📈296Realtime Image/Video Gen AI Arena
-
Voice Clone
🗣2.66kClone a voice and generate speech from text
-
CompassArena
🏢20View the CompassArena platform in a full‑screen web view
-
Phased Consistency Model PCM
🐠104Generate images from text prompts
-
Unique3D
⚡794Create a 1M faces 3D colored model from an image!
-
Open Remove Background Model (ormbg)
💻174Remove background from images
-
YOLO ARENA
🏟50compare performance of top object detectors
-
Chattts Zero
🐢338Generate audio from text with tuning options
-
FineWeb: decanting the web for the finest text data at scale
🍷1.38kExplore and download the FineWeb web‑scale text dataset
-
Consistent Character
🤹647Create images of a given character in different poses
-
Real-time Whisper WebGPU
🎤465Transcribe audio to text instantly using WebGPU
-
ChronoDepth
🔥62Generate depth maps from videos
-
Stable Diffusion 3 Medium
🎨1.64kGenerate custom images from text prompts with Stable Diffusion 3
-
Florence 2
📉845Generate captions, detections, and segmentations for any image
-
MassivelyMultilingualTTS
🌍242Generate natural speech in 7000+ languages
-
Corpus Creator
📁70Transform text files into a Hugging Face dataset
-
Llm Visual Program Sythensis
🐠8Generate Python code from grayscale images using turtle graphics
-
4M Demo
⚡2034M: Massively Multimodal Masked Modeling
-
AuraSR-v2
😻622Upscale your images 4x with high-quality AI enhancement
-
MInference
🌍60Chat with a fast LLaMA‑3 AI using dynamic sparse attention
-
Tile Upscaler
🚀997Upscale and enhance images with tile‑aware AI
-
Video Transcription Smart Summary
⚡371Generate transcription and summary from uploaded videos
-
Flash Lora
⚡157Generate custom images with LoRA‑enhanced Stable Diffusion
-
Better Florence 2
🔥198Analyze images to detect objects, generate captions, or perform OCR
-
Auraflow Demo
🖼250Generate high-quality images from text prompts with AuraFlow
-
Magpie
🐦73Generate and rate instruction-response pairs
-
Whisper Timestamped
🕒224In-browser speech recognition w/ word-level timestamps
-
PhotoMaker V2
📷1.21kGenerate personalized portrait images from your photos and prompts
-
Whisper Speaker Diarization
🗣330Generate speaker‑labeled transcripts from audio files
-
InternVL
⚡512Chat with an AI that understands images and text
-
FLUX.1 [dev]
🖥9.48kGenerate images from text prompts
-
Stable Fast 3D
🎮1.2kGenerate a 3D mesh from a single image
-
FLUX.1 [Schnell]
🏎5.08kGenerate images from text prompts instantly
-
Florence2 + SAM2
🔥518Segment objects in images or videos using text prompts
-
Finegrain Object Eraser (Lite Version)
🧽435Erase any object from an image with just a prompt
-
MindSearch
📊54Ask questions and get detailed answers with visual search graphs
-
FLUX LoRa the Explorer
🏆1.57kCreate AI images with FLUX LoRA styles
-
Background Removal
🌘2.89kRemove backgrounds from images instantly
-
MeshFormer
🌟68Generate 3D mesh from an image
-
Joy Caption Pre Alpha
💬1.46kGenerate descriptive captions for any image
-
ChatTTS Forge
💬301Launch a web interface for text-to-speech and SSML processing
-
FLUX Prompt Generator
😻1.39kLaunch an interactive web interface for the tool
-
Fish Audio S1
🏆696Convert text to natural-sounding speech audio
-
PuLID-FLUX
🤗2.1kGenerate customized images from text and reference photos
-
ArxivCopilot
🏢65Generate personalized research profiles and chat with Arxiv Copilot
-
Diffusers Image Outpaint
🔅2.54kEasily expand image boundaries
-
Multi Voice TTS(English/Chinese/Japanese)
😆150[中文/English/日本語]multilingual text-to-speech
-
GPT SoVITS V2 Pro Plus
🤗243Generate speech from text using a reference voice
-
Flux.1-dev Upscaler
🔎1.69kUpscale low‑resolution images to high‑resolution with AI
-
Open NotebookLM
🎙1.09kPersonalised Podcasts For All - Available in 13 Languages
-
Whisper Turbo
🤯1.02kTranscribe audio or YouTube videos into text
-
Joy Caption Alpha Two
👁1.77kGenerate detailed captions or prompts for any image
-
FacePoke
🙂2.21kImport a portrait, click to move the head!
-
paper-central
⚡229Explore and filter research papers by date, topic, and author
-
Dia 1.6B
👯1.78kGenerate realistic dialogue from a script, using Dia!
-
Describe Anything
⚡344Describe any selected part of an image
-
FramePack图像到视频生成(5秒限制版)
🎬321Generate video from image
-
MotionShop2
🏃181Replace characters in a video with characters in photos
-
Qwen3 Demo
📊857Chat with an AI assistant that thinks before answering
-
WaiNSFWIllustrious V110
🖼552Generate images from detailed text prompts
-
ICEdit
🖼666Universal Image Editing is worth a single LoRA
-
Computer Agent
🖥984Interact with an AI agent to perform web tasks
-
ACE Step
😻664A Step Towards Music Generation Foundation Model
-
FLUX Unlimited
🔥1.42kUse the FLUX model as much as you want.
-
Parakeet-TDT-0.6b-V2
475Transcribe audio files with timestamps and downloadable subtitles
-
NSFW Uncensored text to image/ Image to Image
🎬892NSFW Uncensored text/Image to image for AI Limits
-
DreamO
🐨604A Unified Framework for Image Customization
-
FramePack F1
📹326fast video generation from images & text
-
Joy Caption Beta One
🖼1.1kGenerate custom captions, tags, or prompts for any image
-
LTX Video Fast
🎥1.52kultra-fast video model, LTX 0.9.8 13B distilled
-
Deepdrone
🚀16Authenticate and access DeepDrone command center
-
Step1X 3D
🐨247image2mesh
-
SmolVLM realtime WebGPU
⚡161Ask questions about your webcam view and get text answers
-
MedGemma - Radiology Explainer Demo
🩺245Radiology Image & Report Explainer Demo. Built with MedGemma
-
Realistic Text To Speech Unlimited
🔥1.76kFree Text-To-Speech generator with Emotion control (OpenAI)
-
Wan2.1 Fast
🎥1.61kAnimate a still image into a short video using a prompt
-
BAGEL
🚀222Demo for BAGEL
-
Chatterbox TTS
🍿1.74kExpressive Zeroshot TTS
-
Chain-of-Zoom
🚀321Extreme Super-Resolution via Scale Autoregression
-
SoloSpeech
🎯114State-of-the-art target speech extractor
-
Direct3D S2 V1.0 Demo
💻430Generate large-scale 3D models with spatial sparse attention
-
Conversational WebGPU
🚀234 -
OmniConsistency
🚀215Generate styled image from reference image and external LoRA
-
Dots Demo
💻153Chat with an AI assistant to get helpful text responses
-
Graphify
⚡204Create multiple diagram types instantly from JSON!
-
AI Marketing Content Generator
🎨200An AI-powered tool made for content creators and marketers
-
Sparc3D
🏃1.63kNext-Gen High-Resolution 3D Model Generation
-
Hunyuan3D-2.1
👻2.14kImage-to-3D Generation
-
PartPacker
🪴297Part-level image-to-3D generation.
-
MiniMax M1
💬354Generate web code from your description and view it live
-
Song Prep
🎵744Transcribe song lyrics with timestamps
-
Self Forcing Wan 2.1
🎥326Real-time video generation
-
OmniGen2
👀437OmniGen2: Unified Image Understanding and Generation.
-
FLUX.1 Kontext
⚡1.6kKontext image editing on FLUX[dev]
-
facebook/seamless-interaction
Updated • 44.5k • 190 -
3d-Model-Playground
👀57Control 3D models using gestures and voice
-
Ovis U1 3B
🎨174Demo for multimodal understanding and generation
-
FLUX.1 Kontext LoRA the Explorer
👩170edit images with Kontext and LoRAs
-
Kontext Relight
💡292relight images with Flux Kontext[dev]
-
ThinkSound
🔊320Generate audio for a silent video using text prompts
-
Grok 4 Heavy Free
🏢303Free Grok 4 heavy
-
Miragic Virtual Try On
👕554Try on complete outfits with our virtual try-on technology
-
JarvisArt Preview
🏃105Generate Lightroom presets from images and prompts
-
Web Search MCP
🔎164Search and extract web content for LLM ingestion
-
Higgs Audio Demo
🎤404Higgs Audio Demo
-
Qwen3 Coder WebDev
🌍1.11kGenerate HTML or React code from your web app description
-
Multi-Style Video-to-Anime Generator
📊287Transfer your videos with different AnimeStyles & havefun!
-
MegaTTS 3 Voice Cloning
🎤292MegaTTS 3 but with voice cloning!
-
LLM Embeddings Explained: A Visual and Intuitive Guide
🚀355How Language Models Turn Text into Meaning, From Traditional
-
Qwen3 MT Demo
🏃121Translate text instantly between many languages
-
Wan 2.2 5B
🚀516Generate videos from text prompts and optional images
-
FLUX.1 Krea Dev
📚372Generate images from text prompts
-
Qwen Image
🖼914Generate high-quality images from text prompts
-
OnePoseviaGen
💻289Estimate 3D object pose from a single RGB image
-
OmniAvatar
🐨289Generate podcast and tiktok style video avatars
-
zai-org/GLM-4.5V
Image-Text-to-Text • 108B • Updated • 134k • • 719 -
Wan2.2 14B Fast
🎥3.3kgenerate a video from an image with a text prompt
-
Ovis2.5 9B
📊178High-accuracy vision & reasoning for complex tasks
-
Ovis2.5 2B
📚110Lightweight vision for efficient deployment
-
Qwen Image Edit
✒828Edit images using natural language instructions
-
DINOv3 Web
🦖159Visualize rich, dense image features locally in your browser
-
Bedtime Story Generator
✨173Craft magical tales in seconds.
-
Jupyter Agent 2
🏃253Generate and run a Jupyter notebook from your description
-
ToonComposer
🎨146Create custom videos from text and keyframe images
-
Qwen Image Fast
🖼154Generate images in 8-steps
-
Qwen Image Edit Fast!
✒489Fast 8 step inference of Qwen Image Edit
-
Privacy-Safe Synthetic Data Generation | Syncora AI
🐠511Privacy-safe synthetic data for ML and data augmentation
-
FastVLM WebGPU
🍎446Real-time video captioning powered by FastVLM
-
Nano Banana PRO
🍌743Nano Banana for Hugging Face PRO users
-
USO FLUX
⚡301Generate custom images with style and subject references
-
Wan2.2 S2V
🚀387Generate video from an image and audio file
-
DeepSite Gallery
🏆73Browse apps made with DeepSite
-
HunyuanVideo Foley
🎬163Generate realistic audio for your video using text prompts
-
ID Document Verification
🚀34Recognito ID Document OCR and Liveness Detection
-
Face Recognition Opy
🦀18Verify if two faces match and get similarity score
-
Face Liveness Detection SDK
😉116FaceOnLive On-Premise Solution
-
VibeVoice
🏃179Generate multi‑speaker AI podcasts from a script
-
Chatterbox-Multilingual-TTS
🌎403Chatterbox TTS supporting 23 languages
-
Wan 2 2 First Last Frame
💻649Generate a short video from two images
-
FineVision: Open Data is All You Need
📝232A new open-source dataset for training VLMs
-
Qwen3 ASR Demo
👀262Convert uploaded audio to text with language detection
-
IndexTTS 2 Demo
🏢819Generate expressive speech from text with voice and emotion control
-
Mood Palette Generator
🎨134Mood Palette Generator
-
ReconViaGen
🖥179High-fidelity 3D Geometry Generation from multi-view images
-
NoWatermark
⚡441Powerful Watermark Removal API
-
granite-docling-258M demo
📝279Convert and query documents from images with AI
-
Wan2.2 Animate
👁5.11kWan2.2 Animate
-
Qwen3 Omni Demo
⚡267Chat with AI using text, audio, images, or video
-
Qwen Image Edit 2509
👀324Edit images based on natural language instructions
-
Qwen3 TTS Demo
🚀406Generate spoken audio from your text in many voices
-
SGS 1
🚀136Generate 3D CAD models from images
-
Fka Awesome Chatgpt Prompts Atlas
🗺3Explore and visualize high‑dimensional embeddings interactively
-
Meta Agents Research Environments Demo
🚀49Explore Meta Agents research environments
-
Qwen3 VL Demo
😻451Chat with AI using text and images
-
Qwen3 Livetranslate Demo
🏃139Translate live speech to another language with audio playback
-
ImageEditPro
🐨660AI-powered image editing tool
-
Ostris' AI Toolkit
💻150Train FLUX, Qwen and Wan LoRAs with Ostris Ai Toolkit
-
HunyuanImage-3.0
📊182Generate images from text prompts (PRO users only)
-
Granite-4.0 WebGPU
🪨178Run Granite-4.0-Micro 100% locally in your browser on WebGPU
-
NeuTTS-Air
☁319Clone a voice and generate custom speech
-
Ovi
🔥342Generate a short video with audio from an image and prompt
-
Ovi [local]
🎥270Generate Hollywood Style Actors on your Local Machine
-
Granite Docling 258M WebGPU
🐣160Convert document images to HTML with a single click
-
Sora 2
📉485Generate videos from text or images
-
Reverse Face Search
📉153Search Face Online
-
agentflow
🚀176Solve complex questions with step‑by‑step AI reasoning
-
veo3.1-fast
🐨591Generate videos from text prompts or images
-
AutoPR
🚀20Generate a Twitter or Xiaohongshu post from a research PDF
-
PaddleOCR-VL Online Demo
📈254Extract text, tables, formulas, and charts from images
-
Robot Learning: A Tutorial
📝454Read a comprehensive robot learning tutorial
-
DeepSeek OCR Demo
🆘449An interactive demo for the DeepSeek-OCR model.
-
HunyuanWorld-Mirror
🌍183Universal 3D World Reconstruction with Any Prior Prompting
-
Krea Realtime Video
👁103Generate AI videos from webcam, video, or text
-
DeepSeek OCR 2 Demo
🚀481Try out DeepSeek-OCR-2 on your PDFs or images
-
The Smol Training Playbook
📚3.23kThe secrets to building world-class LLMs
-
Granite 4.0 Nano WebGPU
🛠110In-browser tool calling with IBM Granite-4.0
-
Dream-wan2-2-faster-Pro
🎥1.37kCinematic image-to-video with Wan2.2
-
Qwen Image Edit Camera Control
🎬2.24kFast 4 step inference with Qwen Image Edit 2509
-
Wan2.2 Animate [Local]
🔥300Edit Videos with Wan 2.2
-
Gradio Hackathon Registration Winter 25
📝181Gradio Agents & MCP Hackathon Winter 2025 Registration Page
-
Omnilingual ASR Media Transcription
🌍240Transcribe audio/video files into text instantly
-
Maya1
📉116Demo of our new open source model maya1
-
Image Mashup
🔥127Image Combination Generator
-
Depth Anything 3
🏢432Generate depth maps from your photos
-
Qwen-Image-Edit-2509-LoRAs-Fast
⚡775Demo of the Collection of Qwen Image Edit LoRAs
-
Supertonic (TTS)
⚡222Lightning-Fast, On-Device TTS
-
Qwen-Image-Edit-2509-Photo-to-Anime
🌖195Convert a photo into anime-style artwork
-
FLUX.2 [dev]
💻1.01kGenerate or edit images from text and optional photos
-
Z Image Turbo
🏃1.87kGenerate detailed images from your text prompts
-
Z Image Turbo
🖼3.52kGenerate high-quality images from text prompts
-
Karpathy Llm Council
🏢274Consult a council of LLMs for a refined answer
-
Evaluation Guidebook
📝331Explore LLM benchmark scores over time
-
Ministral WebGPU
⚡133Frontier multimodal AI, running entirely in your browser.
-
VibeVoice-Realtime-0.5B
🐨185Generate natural speech from text with selectable voices
-
Qwen Image to LoRA
😭345Generate LoRA from a single image
-
Anim Lab AI
🔥130Turn boring math into engaging animation videos
-
LongCat Image Edit
👁147Generate and edit images using text prompts
-
Chatterbox Turbo Demo
⚡517Chatterbox Turbo Demo
-
TRELLIS.2
🏢1.78kHigh-fidelity 3D Generation from images
-
Omni Image Editor
🖼2.09kImage edit, text to image, image upscale, remove watermark
-
Qwen Image Layered
🚀527Decompose an image into editable layers
-
FunctionGemma Physics Playground
🕹107Use natural language to solve fun physics simulation puzzles
-
Qwen Image Edit 2511
🏆426Edit images using natural language instructions
-
Qwen Image Edit 2511 Fast
🏆264Fast 4 step inference of Qwen Image Edit 2511
-
Qwen-Image-Edit-2511-LoRAs-Fast
🎃1.87kDemo of the Collection of Qwen Image Edit LoRAs
-
HY-Motion-1.0
💃289Text-to-3D and Image-to-3D Generation
-
Qwen Image 2512
👀376Rewrite image prompts into detailed English descriptions
-
Qwen Image Multiple Angles 3D Camera
🎥2.61kTransform image viewpoint with adjustable camera angles
-
Qwen Edit Any Pose
🕺401Edit any pose with Qwen Edit 2511 Any Pose LoRA
-
Wan2.2 14B Preview
🐌2.85kgenerate a video from an image with a text prompt
-
LTX-2 Video Fast
🎥217Fast high quality video with audio generation
-
FLUX.2 [Klein] 9B
💻925Generate or edit images from text prompts
-
Supertonic 2 (TTS)
⚡195Lightning-Fast, On-Device, Multilingual TTS
-
Demo Playground
⚡823Free platform to access multiple AI models
-
Qwen3-TTS Demo
🎙2.02kGenerate speech from text using voice design, cloning or presets
-
kyutai/pocket-tts
⚡179Pocket TTS optimized for Hugging Face Spaces on CPU
-
Qwen Image Edit Object Manipulator
🔥216Text-Guided Object Manipulation Using Qwen Image Edit + LoRA
-
Voxtral Mini Realtime
🎤155Transcribe speech to text instantly in real time
-
ACE-Step v1.5
🎵560Music Generation Foundation Model v1.5
-
Reachy Phone Home
📱358Phone focus companion for Reachy Mini
-
Baby Reachy-Mini Companion
🤖171A fully local Reachy Mini AI Companion for babies and kids.
-
Omni Video Factory
🏆1.29ktext to video, image to video, video extend
-
FireRed Image Edit 1.0
🌍240FireRed-Image-Edit-1.0
-
SoulX-Singer
🎤170Generate singing voice from lyrics and convert vocals
-
faster-qwen3-tts
🎙253Generate natural speech from text with Qwen3
-
FireRed Image Edit 1.0 Fast
🌖1.5kFireRed-Image-Edit × Qwen-Image-Edit-Rapid (Transformers)
-
The Synthetic Data Playbook: Generating Trillions of the Finest Tokens
📝264Visualize synthetic‑data experiments as an interactive bookshelf
-
OBLITERATUS
💥399One-click model liberation + chat playground
-
LTX 2.3 Distilled
📚395Generate cinematic videos with audio from text prompts
-
Free Unlimited Google Veo 3
🌖457Free Unlimited Google Veo-3 NSFW Uncensored
-
TADA
🎵85Generate voice‑cloned speech from a short audio prompt
-
Fish Audio S2 Pro
🐟160Zero GPU Text-to-Speech using Fish Audio S2 Pro
-
DLSS 5 Anything
🎮385Turn any image into a DLSS 5 meme (using FLUX.2-klein-9b-kv)
-
FLUX.2 Klein 9B KV
🎨216Generate or edit images from text and optional photos
-
Kimodo
🏃275Generate high-quality motions from text prompts
-
Voxtral TTS Demo
⚡216Generate realistic speech from text
-
daVinci-MagiHuman
🎬166Generate short videos from an image and text prompt
-
OmniVoice
🌍1.09kHigh-quality voice cloning TTS for 600+ languages
-
Wan2.2 14B Fast Preview
🐌2.01kgenerate a video from an image with a text prompt
-
Gemma 4 WebGPU
🚀235Run Gemma 4 locally in-browser on WebGPU w/ Transformers.js
-
VoxCPM Demo
🎙658VoxCPM2 Nano-vLLM Demo
-
Unfolding Robotics: Open-Source Shirt Folding from Data to Deployment
🤖125Explore the open-source guide to robot shirt folding
-
Bonsai 1-bit WebGPU
🌳182Run 1-bit Bonsai LLMs locally in your browser on WebGPU
-
Bonsai {1, 1.58}-bit GPU
🌿102Run {1, 1.58}-bit Bonsai LLMs on GPUs
-
Distilling 100B+ Models 40x Faster with TRL
📝91TRL distillation for 100B+ teachers, 40x faster
-
ace-step-jam
🎧146Describe any song — AI writes & produces it
-
ERNIE Image
👁150ERNIE-Image Demo
-
Ternary Bonsai WebGPU
🌳149Run 1.58-bit Bonsai LLMs locally in your browser on WebGPU
-
ML Intern
🤖414Explore machine learning tasks via an interactive web app
-
The ultimate guide to RL environments: building and scaling them in the LLM era
📝197Building and scaling RL environments for LLM training
-
Survival Island Game
🏝78Watch an AI survive on a procedurally generated island
-
Wan2.2 14B Preview
🐌201generate a video from an image with a text prompt
-
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P
🔥361This Space uses ''HauhauCS/Gemma-4-E4B-Uncensored-Hauh...''.
-
Pixal3D
🏆326High-fidelity pixel-aligned image-to-3D generation.
-
Supertonic 3 (TTS)
⚡242Lightning-Fast, On-Device, Multilingual, Accurate TTS
-
HiDream O1 Image
🚀139Generate custom images from text prompts
-
LTX 2.3 Studio
🎬281Generate videos from text, images, audio, or video clips
-
Fast Image Studio
🚀97fast image editing using FireRed Image Edit and gr.Server
-
Wan2.2 14B Fast Preview
🐌227generate a video from an image with a text prompt
-
Carbon
🧬173Explore DNA model predictions and protein folding interactively
-
DramaBox
🎭110Expressive TTS with voice cloning — DramaBox demo
-
Qwen Image Edit 2509 LoRAs Fast
⚡222Demo of the Collection of Qwen Image Editing LoRAs
-
LongCat-Video-Avatar 1.5
🎤277Audio-driven talking-head video generation (Meituan LongCat)
-
Bonsai Image WebGPU
🌳310State-of-the-art image generation, in your browser.
-
Lance
🎬114Generate, edit, and understand images and videos with Lance!
-
LocateAnything
💬395Detect and label objects in images and videos
-
L2P - Z-Image 6B Pixel-Space
🎨62End-to-end pixel-space 6B diffusion via L2P
-
TripoSplat
👁287Generate 3D Gaussian models from a single image
-
Ideogram 4
🎨227Ideogram 4 state of the art open weights
-
LTX 2.3 Finetuned I2V
🎬294LTX 2.3 finetuned I2V with identity & voice conditioning
-
Fast Gemma Challenge
⚡93Multi-agent collab to make Gemma go brrr
-
Small Talk
🎙131An AI-to-AI robot podcast hosted by Reachy Minis
-
Gemma Diffusion Website Builder
🌐67Watch a diffusion LLM write a website live, then tweak it
-
Gemma 4 WebGPU Kernels
⚡287Chat with Gemma 4 E2B AI model in your browser
-
OpenMythos
🛡155An Open Source Cyber Security Agent
-
Pro Realism Edit Studio
🎨449Powerful image editing - supports one or two input images.
-
Jigarzzz Video Suite
🚀153Free voice gen, video gen & anti-copyright yt
-
Unlimited OCR
🏆194Extract text from images and PDFs instantly
-
Wan2.2 14B Fast Preview
🐌376generate a video from an image with a text prompt
-
Krea 2
🎨140Krea 2 text-to-image (Raw + Turbo)
-
Boogu Image
🍊75Boogu-Image-0.1-Edit and Edit-Turbo
-
CUGA Apps
🚀592 dozen real-life agents optimized for open models & stack
-
FLUX.2 Klein multi-LoRA
🥚130Use multiple FLUX.2-Klein LoRAs
-
LFM2 WebGPU Kernels
💧65Run LFM2.5 230M with custom WebGPU kernels
-
HF Realtime Voice
🎙296Voice chat over WebSocket against a HF speech-to-speech
-
ProtectBirds
🏃864Protect Birds
-
Don't Train the Model, Evolve the Harness
🌿45Evolving an agent's harness, not its model, on Harvey's LAB