google/ddpm-ema-church-256
Unconditional Image Generation • Updated • 1.63k • 18
ddpm
-
-
stabilityai/sd-x2-latent-upscaler
0.4B • Updated • 2.84k • 189 -
stabilityai/stable-diffusion-x4-upscaler
0.5B • Updated • 5.89k • 730 -
lllyasviel/sd-controlnet-canny
Image-to-Image • 0.4B • Updated • 27.9k • 252 -
tencent/Hunyuan3D-2.1
Image-to-3D • Updated • 72.7k • 1.29k -
alimama-creative/FLUX.1-Turbo-Alpha
Text-to-Image • 0.3B • Updated • 14.2k • 644 -
kudzueye/boreal-qwen-image
Text-to-Image • Updated • 1.75k • • 129 -
prithivMLmods/Qwen-Image-HeadshotX
Text-to-Image • Updated • 175 • • 42 -
drbaph/Qwen-Image-Edit-Mannequin-Clipper-LoRA
Image-to-Image • Updated • 95 • • 78 -
Stable-X/trellis-normal-v0-1
Image-to-3D • Updated • 15.6k • 15 -
Stable Fast 3D
🎮1.23kGenerate a 3D mesh from a single image
-
meta-llama/Llama-2-70b-chat-hf
Text Generation • 69B • Updated • 4.56k • 2.21k -
DeepSite v4
🐳16.6kGenerate any application by Vibe Coding it
-
stabilityai/stable-point-aware-3d
Image-to-3D • 2B • Updated • 6.41k • 418 -
zai-org/GLM-4.7
Text Generation • 358B • Updated • 82.8k • • 2.07k -
MiniMaxAI/MiniMax-M2.1
Text Generation • 229B • Updated • 10.6k • • 1.37k -
Image Upscaling Playground
🦆874Upscale images with selectable super‑resolution models
-
TRELLIS.2
🏢2.24kHigh-fidelity 3D Generation from images
-
Face Swap
👩846Image deep fake (uncensored)
-
fishaudio/s2-pro
Text-to-Speech • 5B • Updated • 33.8k • 1.45k -
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
Image-Text-to-Text • 28B • Updated • 22.3k • • 2.96k -
Ethos Studio
🎤26Transcribe audio/video with speaker and emotion analysis
-
TB Guard XAI
🏥1Analyze chest X-rays for TB with AI explanations
-
ChatCraft
🎮31v1 RTS game controlled by voice via Mistral
-
hacker_radio
📻 -
Universal Memory Agent
🚀1Chat with a memory‑enabled AI that remembers your facts
-
Istral Ai Demo
🐨4Chat with a Mistral‑powered AI assistant
-
HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive
9B • Updated • 701k • 2.3k -
HuggingFaceFW/finephrase
Viewer • Updated • 1.02B • 112k • 157 -
LTX 2.3 Outpaint
🌠35expand videos to any aspect ratio with LTX 2.3
-
ERNIE Image
👁152ERNIE-Image Demo
-
AniGen
🚀80Generate animatable and articulated 3D assets from images
-
MOSS TTS Nano
📈76ZeroGPU Nano-TTS voice clone demo
-
Ternary Bonsai WebGPU
🌳163Run 1.58-bit Bonsai LLMs locally in your browser on WebGPU
-
Audio Flamingo Next
🔊37Generate detailed answers from uploaded audio or YouTube videos
-
HY World 2.0 Demo
🤗64A Multi-Modal World Model for Reconstruction
-
ace-step-jam
🎧167Describe any song — AI writes & produces it
-
ML Intern
🤖423Notify users that ML Intern has moved to HuggingChat
-
Z Image Turbo
🖼3.91kGenerate images from text prompts in seconds
-
Omni Image Editor
🖼2.81kImage edit, text to image, image upscale, remove watermark
-
CogVideoX-2B
🎥460Text-to-Video
-
zai-org/CogVideoX-2b
Text-to-Video • 2B • Updated • 15.9k • 380 -
zai-org/GLM-5.1
Text Generation • 754B • Updated • 547k • • 1.85k -
anicka/geometric-euphorics
Text Generation • Updated • 1 -
My Pi Agent
🦀69Chat with a coding assistant powered by a hosted AI model
-
Epicure Explorer
🌶64Operators behind the FlavourBench culinary benchmark
-
RF-DETR Realtime Webcam Demo
🎯59Segment objects in live webcam and uploaded media
-
Sdxl2
🚀19Execute custom Python code
-
DeepSite
🐳442Imagine and Share in 1-Click
-
AnyCoder
🏆3.32kGenerate code snippets with AI for web and app frameworks
-
Uncensored HackerCoding GPT
📉392This Is For Educational Purpose, I am not responsible!!
-
UncensoredChat
💻761Chat with XORTRON - Criminal Computing
-
UGI Index
🏆17A holistic ranking of Uncensored LLMs
-
coder3101/gemma-4-31B-it-heretic
Image-Text-to-Text • 31B • Updated • 2.24k • • 89 -
Map Anything (v1)
🏃11Universal Feed-Forward Metric 3D Reconstruction
-
TRELLIS
🏢769Scalable and Versatile 3D Generation from images
-
TRELLIS.2-Text-to-3D (Rerun)
🔥54Text-to-Image → 3D or Image-to-3D
-
TripoSR + Dust3R
🎨6Image to 3D + Multi-view Point Cloud
-
SAM 3D Objects MCP
📦6Image + Mask → 3D Object (GLB) - MCP Server
-
Shap-E
🧢560text-to-3D & image-to-3D
-
Pixel3dmm [Image Mode]
📷102Versatile Single-Image 3D Face Reconstruction
-
SAM 3D Body MCP
🧍20Image → 3D Human Mesh (GLB) - MCP Server
-
Dream-wan2-2-faster-Pro
🎥1.4kCinematic image-to-video with Wan2.2
-
Qwen-Image-Edit-2511-LoRAs-Fast
🎃2.78kDemo of the Collection of Qwen Image Edit LoRAs
-
CodeFormer
📊4Image face enhancer
-
高画質AI画像編集
📷34High-resolution 2K image editing with FireRed
-
Color Grade Transfer
😻13Apply the color grade from one image to another image
-
MCP Plausible
🌖4MCP Server to check website stats via Plausible Stats API.
-
PiD Image Upscaler
🥖73Pixel-Diffusion Decoder
-
PASD Magnify
✨248Magnify subject details and enhance image quality
-
Background Removal
🌘2.97kRemove backgrounds from images instantly
-
Rembg
⚡6image background removal
-
BiRefNet - Background Removal
✂8Remove image backgrounds and get a transparent PNG.
-
CorridorKey
🎬2Remove green/blue screen from video, even glass & hair
-
orcarouter/Qwen3.8-27B-Uncensored-FP8
Image-Text-to-Text • 28B • Updated • 128k • 1.82k -
CohereLabs/North-Mini-Code-1.0
Text Generation • 30B • Updated • 7.37k • 581 -
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 490k • • 1.3k -
Qwen/Qwen3-Coder-Next
Text Generation • 80B • Updated • 498k • • 1.7k -
VLM Parsing
📄13for document parsing task
-
JoyAI Video Edit (Live)
🎬61Real-time webcam video editing (ZeroGPU)
-
Audio8 TTS Preview 0.1B
🗣25Zero-shot voice cloning TTS with Audio8 0.1B
-
Look Who's Talking
👀6In a group, Reachy looks at whoever is talking. 100% local.
-
Microduck Sandbox
🐤636Showcase a bold landing page with stylized title and button
-
TinyCodeAgent
🐣28Think in python and execute code to solve a task
-
Qwen3.8 27B Object Detection
⚗32Unleash the Power of Visual Grounding
-
MiniMax-H3 Inpainting
🖌33Say what to change in a clip and MiniMax-H3 repaints it
-
MiniMax-H3 Audio to Video
🔊50A first frame plus your own soundtrack, driving MiniMax-H3
-
pyannote/speaker-diarization-3.1
Automatic Speech Recognition • Updated • 6.77M • 4.46k -
pyannote/segmentation-3.0
Voice Activity Detection • Updated • 5.17M • 2.28k -
pyannote/speaker-diarization-community-1
Automatic Speech Recognition • Updated • 5.22M • 3.09k -
Qwen/Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 7.7M • • 18k -
4DAnyone × Rerun
🕺28One monocular clip of a person becomes six novel views
-
Krea 2 Turbo SDA Diversity LoRA
🎲33Same prompt, many seeds - diversity LoRA for Krea 2 Turbo
-
H3 Acceleration Arena
🥇155Blind A/B ranking of MiniMax-H3 acceleration variants
-
ABot-Recon Streaming 3D
🏗44Streaming 3D reconstruction from video with local context
-
Viggle-Animate
🕺84Put the person from a still into a driving video, in 4 steps
-
orcarouter/Qwen3.8-27B-Uncensored
Image-Text-to-Text • 28B • Updated • 22.7k • 466 -
VibeVoice ASR BitNet
🎙39Multilingual CPU-only ASR with a 1.58-bit BitNet decoder
-
A.X K2 Raon-Speech 21B-A3B
🗣26Bilingual EN/KO speech LM - transcribe, ask, and speak
-
CharacterSheet LoRA Demo
🧑211Multi-view character sheet from one image (FLUX.2 LoRA)
-
Laguna S 2.1
🌖29Chat with Laguna S 2.1 model in a terminal‑style web interface
-
NeuTTS-2E
😻36Low-resource speech synthesis with emotional control!
-
NeuTTS-Nano Multilingual Collection
🌍52Generate speech with voice cloning, now in four languages!
-
NeuTTS-Air
☁324Generate speech in a chosen voice from reference audio
-
BizGenEval Leaderboard
🥇4Official BizGenEval leaderboard on Hugging Face.
-
PazaBench
🥇29ASR Leaderboard for low resource languages
-
MageBench Leaderboard
🥇17This is a leaderboard for magebench
-
Bonsai 27B WebGPU Kernels
🌳473Run a 1-bit 27B LLM locally in your browser on WebGPU
-
deepseek-ai/DeepSeek-V4.1-Flash
Image-Text-to-Text • 763B • Updated • 1.32M • • 4.64k -
Mage-VL
🎞109Codec-native video & image understanding with Mage-VL 4B
-
Inflect v2 — Tiny Local TTS
🔊118Run complete 3.96M and 9.36M text-to-waveform models live.
-
ARDY Motion Playground
🕺41Text-to-motion with an interactive 3D skeleton playground
-
MOSS-VL-Realtime
👁33Realtime VLM for image and video understanding
-
Hy3
⚡63Hy3 multi-turn streaming chat with function calling
-
Hunyuan3D-2.0
🌍3.41kText-to-3D and Image-to-3D Generation
-
Song Prep
🎵753Transcribe song lyrics with timestamps
-
Hunyuan3D 2mini Turbo
🔥232Fast Images-to-3D Generation within 1 Second
-
DepthCrafter
🦀210a super consistent video depth model
-
AuK
🎙127Unified speech generation and editing with AuK
-
HY-Motion-1.0
💃307Text-to-3D and Image-to-3D Generation
-
HY-Embodied-0.5
🤖6Official chatbot demo for Tencent HY-Embodied-0.5
-
Youtu-Parsing
🚀19Try out Youtu-Parsing on your PDFs or images
-
HunyuanWorld-Mirror
🌍196Universal 3D World Reconstruction with Any Prior Prompting
-
Hunyuan3D Part
☯80Segment and generate parts from a 3D mesh
-
Krea 2 Outpaint
🖼118Extend images into larger canvases with Krea 2 outpaint
-
Hunyuan3D 2mv Turbo
🌍334MultiImages-to-3D Generation
-
Nemotron-Labs-Audex
🎧66Unified audio-text intelligence
-
OvisOCR2
🔎117Stream structured Markdown from document images and PDFs.
-
LTX-Best-Face-ID
🎬54Distilled LTX-2.3 identity video from a reference photo
-
Hunyuan3D-2.1
👻2.31kImage-to-3D Generation
-
HunyuanVideo Foley
🎬172Generate realistic audio for your video using text prompts
-
Krea 2 Identity Edit
🧬262Identity-preserving instruction image editing on Krea 2
-
Hunyuan Large
💬228Hunyuan-Large模型体验
-
Hunyuan Turbos
💬78hunyuan-turbos模型体验
-
Hunyuan T1
💬233Hunyuan T1模型体验
-
InfiniSplat
🌌109Single-image Gaussian reconstruction
-
LFM2.5 Edge Research Agent
🔬80Run an on-device LFM2.5 research agent with WebGPU
-
MiniMax H3
🎬321Video generation with a synchronized soundtrack
-
Cinematic Storyboard Generator
🎬59Generate 8-panel cinematic storyboards from text prompts
-
Agent Memory Leaderboard
🧠979Unified memory evaluation · Results expected August 12.
-
SpotSound Temporal Grounding
🔍36Find when a described sound happens in a recording
-
Video-ORA-9B
🎯18Explore all seven Video-ORA task families
-
FireRedAudio
🔥35Voice cloning, voice design, speech editing and ASR
-
Breeze TTS 2
🎙97Bilingual TTS with voice design, cloning, and direction
-
LTX Ripple
🎬46Edit one frame, ripple the change through the whole video
-
ProCreations/auto-1b
Text Classification • 1B • Updated • 40 • 16 -
ProCreations/grug-27b
Text Generation • 27B • Updated • 2.49k • • 101 -
ProCreations/grug-35b-v2
Text Generation • 35B • Updated • 178 • 20 -
FireRedTTS3
🔥68Voice cloning, voice design and speech editing
-
MiniMax Music 3 Studio
🎵359Generate custom music tracks from text captions and lyrics
-
Wushu Action LoRA · MiniMax-H3
🥋2Martial-arts action video+audio with MiniMax-H3
-
OracleZoom Super Resolution
🔎4Moved — use the authors' Space dipta007/OracleZoom
-
Better Human Motion · MiniMax-H3 LoRA
🏃1Human-motion LoRA on MiniMax-H3 — video + stereo audio
-
TeleOCR
📄40Parse digital & photographed documents into Markdown
-
SyncWorld Simulator
🦾1Visually-calibrated zero-shot robot world simulator
-
Sentimental-0.2M
🎭1190K-param sentiment classifier (Neg/Neu/Pos)
-
UniWorld-View
🛸1Large-baseline novel view synthesis from one image
-
TransVLM Shot Transition Detection
🎬1Detect hard cuts and gradual shot transitions in video
-
NeoMME 260M Retriever
🔎1Late-interaction visual document retrieval with NeoMME
-
Wan2.2 Animate 2 14B
🕺58Animate a character image with a driving video
-
Krea 2 Turbo BBox
🧩58Layout-controlled comics with a draggable bbox canvas
-
Qwen3-TTS Emotion Tags
🎭1Emotion-tag control for Qwen3-TTS via inline transcript tags
-
GLiFormer Large v1
🧩6Entities, classes, relations, records & embeddings
-
Kokoro Inno Clone Tuner
🎙5Zero-shot voice tuning for Kokoro-82M from a reference clip
-
NASA-IBM Lunar Foundation Model
🌑2Any-to-any cross-modal generation for the Moon
-
MiDashengLM-Gen
🎵29Unified audio scene generation from text descriptions
-
MiniMax-H3 Reference Custom Lora
🎭38MiniMax-H3 with 4-8 step Turbo LoRAs, ComfyUI LoRA support
-
Qwen3.8 27B
💻92Chat with Qwen3.8-27B using this hosted demo.
-
LTX-2.5
⚗75LTX-2.5 distilled two-stage
-
LTX-2.3 Clean Plate (Remove People from Video)
🎬13Remove people & vehicles from video, keep the background
-
LTX 2.3 Pixel Spatial Upscaler
🎞14Generative 4x video upscaling with LTX-2.3 IC-LoRA
-
LTX-2.3 Relight (Video Relighting IC-LoRA)
💡7Relight exterior video clips with a light-direction ball
-
LTX Video Fast
🎥1.61kultra-fast video model, LTX 0.9.8 13B distilled
-
Granite Speech Streaming Webgpu
🌍18Granite Speech 5.0 Turbo CTC Streaming Audio Demo
-
Granite 4.0 Nano WebGPU
🛠112In-browser tool calling with IBM Granite-4.0
-
Granite-4.0 WebGPU
🪨179Run Granite-4.0-Micro 100% locally in your browser on WebGPU
-
Granite 3.1 8b Instruct
📝23Chat with IBM Granite 3.1 8b Instruct
-
CIVOS: Emergence or Recitation?
🌍48Do LLM agents discover, or recite memorized history?
-
SenseNova-U1.5-8B-MoT
🎨135Unified text-to-image and image editing model
-
MiniMax-Music3-Jam
🎤106Describe any song, MiniMax Music 3 writes & sings it
-
Gemma 4 - Vision Token Budget
🖼63Resize images for visual token budgets while keeping aspect ratio
-
LingBot-Video MoE 30B-A3B
🎬58Embodied MoE video generation — T2V, I2V, T2I
-
fofr/flux-handwriting
Text-to-Image • Updated • 128 • • 140 -
alvdansen/littletinies
Text-to-Image • Updated • 283 • • 424 -
LTX-2 Video Fast
🎥222Fast high quality video with audio generation
-
Muse-Glimmer-30B
⚡4Try Muse-Glimmer-30B using this hosted demo.
-
Qwen3.8 Flash Next
👀15Chat with Qwen3.8 Flash Next using this hosted demo.
-
Granite Docling 258M WebGPU
🐣162Convert document images to HTML with a single click
-
ibm-granite/granite-guardian-4.1-8b
Text Generation • 8B • Updated • 55.4k • 50 -
Moonshotai Kimi K2.7 Code
💬1kimi2.7 tester
-
Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction
Paper • 2603.29023 • Published • 2 -
The Missing Knowledge Layer in Cognitive Architectures for AI Agents
Paper • 2604.11364 • Published • 2 -
The Making of THE ODYSSEY (ASCII)
🏺3Create an ASCII‑art film from a short text prompt
-
UniSE Speech Enhancement
🔊77Unified AR-LM-based speech enhancement & separation
-
Pulpie
🍊48Clean HTML into Markdown, live at usefeyn.com/pulpie
-
GEPARD
🐆40Spotted text-to-speech with voice cloning and text-CFG
-
ibm-granite/granitelib-core-r1.0
Text Generation • Updated • 3.64k • 36 -
ibm-granite/granitelib-rag-r1.0
14.4M • Updated • 5.24k • 54 -
Zero-Token Confidence
🧠1An LLM that stops when it does not know — at zero token cost
-
SAGA Micro-Drama VLM
🎬1Structure-aware micro-drama video understanding (SAGA)
-
Insta / TikTok Aesthetics · MiniMax-H3 LoRA
📱5Vertical social-video style LoRA for MiniMax-H3
-
LingBot-World-V2 1.3B
🌍1Camera-controlled image-to-video world model (1.3B)
-
MiniMax-H3 VR180 Stereo LoRA
🥽2Text to headset-ready VR180 3D video with audio
-
MiniMax-H3 LMS Sharpen
🔎3Re-render a clip sharper with MiniMax-H3's LMS LoRA
-
Bar-JEPA — Bar Chart Value Extraction
📊1Recover numeric values from bar chart images
-
SpatialBlock
🧱1Spatial intelligence in LVLMs via synthetic block-stacking
-
Xiaomi Robotics U0 4B
🤖1Autoregressive text-to-image and image editing
-
YuE2-3B Music Generator
🎵221Generate songs and covers from style prompts and lyrics.
-
markov-ai/cad-1000-hours
Preview • Updated • 130k • 564 -
nyu-mll/glue
Viewer • Updated • 1.49M • 668k • 1.15k -
StepAudio 3 Music Studio
🎵221Create songs, arrange vocals, and remix music with StepFun
-
How to turn a game into an RL environment
🌍71From an idea to a trained 4B, with the dead ends left in
-
MiniCPM5-2B WebGPU Pi
🥧104A coding agent running entirely in your browser
-
Marigold V2
🌼129Depth, surface normals, and albedo from a single image
-
Join the Agent Swarm
⚡43Collaborative, lossless enwik8 compression research
-
A Hitchhiker's Guide to the 3D Ecosystem
💡93An interactive guide to 3D representations.
-
MiniMax H3 Turbo LoRA
🎬1.73kVideo generation with a synchronized soundtrack
-
Qwen-Image-Edit-2511-LoRAs-Fast
🎃713AnyPose pose still with a strong pose-reference lock
-
AI Notes
📝159Source-grounded AI notes with citations (open source).
-
Wan2.2 14B Fast
🎥3.76kgenerate a video from an image with a text prompt
-
Fruit Fly Simulation
🪰165Simulate a fruit fly in your browser using WebGPU kernels
-
Global LLM Download Leaderboard
🌍50HF text-generation, trailing 30-day downloads by country
-
snkii/Sori-1B-MCQ
Audio-Text-to-Text • 1B • Updated • 71 • 6 -
answerdotai/ModernBERT-large
Fill-Mask • 0.4B • Updated • 754k • 500 -
gamma-lab-umd/MMAU-test-mini
Viewer • Updated • 1k • 2.67k • 3 -
gamma-lab-umd/MMAU-Pro
Viewer • Updated • 5.31k • 5.05k • 22 -
answerdotai/llama3-8b-instruct-CLA-3
Text Generation • Updated • 30 • 2 -
answerdotai/LateOn-regularized-onnx
Updated • 1 -
openjev
⚡50NLI cross-encoder for text and images
-
DiffusionGemma Free Decision Endpoint
🎯12Generate structured decisions from text or images with one API call
-
Qwen-Image-2.1 Prompt Enhancer
✍10Official prompt rewriters for Qwen-Image-2.1, kept warm
-
Qwen-Image-2.1
🖼182Generate and edit images with Qwen-Image-2.1
-
darkc0de/space-factory-runs
184 Bytes -
darkc0de/XortronCriminalComputingConfig
Text Generation • 24B • Updated • 366 • • 180 -
mistralai/Mistral-Large-Instruct-2411
123B • Updated • 9.91k • 283 -
darkc0de/XORTRON.CriminalComputing.LARGE.2026.3
Text Generation • 123B • Updated • 622 • 83 -
Ternary Bonsai 2 WebGPU Kernels
🌳157Run Ternary-Bonsai-2-27B locally in your browser on WebGPU
-
p-e-w/gemma-3-12b-it-heretic
Image-Text-to-Text • 12B • Updated • 663 • • 119 -
Gemma 3 12B IT Heretic Demo
🧪1Multimodal chat demo for Gemma 3 12B Heretic
-
p-e-w/gemma-3-270m-it-heretic
Text Generation • 0.3B • Updated • 134 • 15 -
unsloth/Qwen3.8-27B-GGUF
27B • Updated • 6.77M • 5.18k -
convaiinnovations/laya
Text Classification • 0.4B • Updated • 51.5k • • 5.7k -
Altworld/Hemmingway-1
Text Generation • 27B • Updated • 12.4k • 880 -
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
Image-Text-to-Text • 27B • Updated • 1.76M • 1.86k -
yandex/AliceAI-Foundation-80B-A3B-Base
Text Generation • 81B • Updated • 6.3k • 391 -
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Image-Text-to-Text • 9B • Updated • 26.9k • 660 -
dealignai/Bonsai-2-27B-Ternary-CRACK-GGUF
Text Generation • 27B • Updated • 91.5k • 164 -
pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-GGUF
8B • Updated • 257k • 357 -
OBLITERATUS/Qwen3.8-27B-OBLITERATED
Text Generation • 28B • Updated • 567k • • 1.49k -
dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8
Image-Text-to-Text • 763B • Updated • 52.9k • 714 -
DeepSeek V4.1 Flash UNCENSORED Demo
⚡4Browser demo for DeepSeek-V4.1-Flash UNCENSORED-FP8
-
orcarouter/Qwen3.8-27B-Uncensored-GGUF
Image-Text-to-Text • 27B • Updated • 98.3k • 1.54k -
IQuestLab/IQuest-Q1
Text Generation • 320B • Updated • 3.48k • 146 -
convaiinnovations/laya-multilingual
Text Classification • 0.3B • Updated • 12.9k • • 398 -
convaiinnovations/qwen-api-fastapi
Updated • 3 -
Laya Demo
🎯277Fast System 1 decisions with calibrated probabilities
-
Ming-Image 0.1 Design
🎨59Text-to-image model for UI, infographics and poster design
-
inclusionAI/Ling-3.0-flash-dspark
Text Generation • 1B • Updated • 1.53k • 21 -
LLaDA-UI
🖱2GUI grounding & agent with a block-diffusion VLM
-
Gate Arcade
🚦59Plain vs JEV vs ZTC: a gate decides execute or hold
-
Typed Decision Leaderboard
🎯45JEV & open-Jev answer verifiers, one identical test set
-
Qwen-Image 2.1 Move
🎁56Move & resize objects with Qwen-Image 2.1 turbo, no LoRA
-
XingChen-AGI/TeleOCR
Image-Text-to-Text • 1B • Updated • 38.3k • 1.3k -
XiaomiMiMo/MiMo-V2.6-RL-oss
Viewer • Updated • 7.68k • 172k • 974 -
FLUX.2 Klein Multi LoRA V2
🌍120Experimental space for image editing with FLUX.2 Klein 9B
-
vectara/hallucination_evaluation_model
Text Classification • 0.1B • Updated • 135k • 369 -
HHEM Hallucination Detector
🔍2Is this LLM output faithful to its source? Free open HHEM.
-
Hallucination Detection For Legal LLM Input Output-CERT Vs HHEM
⚖2Detect LLM hallucinations in legal AI outputs.
-
RAG Pipeline Demo
🤖1Find university information using AI
-
gradeops
🚀1Grade assignments automatically with rubrics and audit trail
-
Ai Output Auditor
📉2Check whether an AI answer is supported by your source text
-
Hallucination Evaluation Leaderboard
⚡70View the Vectara leaderboard online
-
LLM Hallucination Leaderboard
📊203Hallucination rates of leading LLMs, scored by HHEM
-
Semantic Image Field
🌄64Multimodal Jev (a.k.a. CLIP)
-
nvidia/Nemotron-3-Diarization
Voice Activity Detection • 99.2M • Updated • 98.7k • 791 -
Live Speaker Diarization
🎙111Identify and label speakers in audio recordings
-
NeMo Speech Streaming Multispeaker ASR
🏢6Shows how to implement streaming multi-speaker ASR
-
HF Viewer · Model Architecture Explorer
🟩177Interactive architecture graph for any HF model
-
Number of VAD models on the Hub
📈1Monthly voice activity detection models on the Hub, with lan
-
runanywhere/silero-vad-v5
Voice Activity Detection • Updated • 12 -
AsccendiaAI/v1-5-pruned-emaonly.ckpt
Updated • 10 -
Dean000111/v1-5-pruned-emaonly.ckpt
Updated -
stable-diffusion-v1-5/stable-diffusion-v1-5
Text-to-Image • 0.9B • Updated • 1.29M • 1.33k -
UncensoredLLMRouter
💬2uncensored llms with openrouter compatible api
-
Cloudflare/clef
Image-Text-to-Text • 27B • Updated • 21.1k • 2.22k -
google/embeddinggemma-2
Feature Extraction • 0.7B • Updated • 164k • • 2.66k -
jialinyyzz/humanizer
Text Generation • 12B • Updated • 104k • 1.95k -
humanizer
✍37Rewrite AI drafts to read like a person; facts kept. 12B
-
Aleph-Alpha/Kolibri-1
Text Generation • 78B • Updated • 19.5k • 956 -
CPU LM Speed Benchmark
⚡11Benchmark base LMs (10M–1B) on CPU — speed and quality
-
Pretty Speed Index
👀5Explore CPU benchmark speeds of small language models
-
Tiny T2I Leaderboard
🚀8Explore and compare tiny text-to-image models
-
Dearcat/PathTrove
Viewer • Updated • 704 • 2.15k • 2 -
Dearcat/hf_cpath_wiki_upload
Updated • 14 -
Warzi/turfin-data
Viewer • Updated • 197 • 44 -
S1MB Leaderboard
📊76Compare System One models across 100+ specialized benchmarks
-
openjev/openjev
Zero-Shot Classification • 27B • Updated • 6.41k • 152 -
openjev/openjev-FP8
Zero-Shot Classification • 27B • Updated • 12.5k • 8 -
openjev-server
⚖2A decision API over any open model, one pass per question
-
Open LLM Leaderboard
🏆14.2kTrack, rank and evaluate open LLMs and chatbots
-
LightOnOCR-3 Demo
🦉75OCR to Markdown with layout grounding
-
colgrep --agent, recorded sessions
🔎6Watch colgrep-agent-2B search a repository, turn by turn
-
LightOn-rerank-PW
✨5LightOn multimodal document reranker with pointwise scoring
-
LightOn-rerank-LW
✨2Compare and rerank four text passages or document pages
-
OriOn Leaderboard
🌖1Leaderboard for all OriOn training runs for reproducibility!
-
dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8
Image-Text-to-Text • 763B • Updated • 69
