Open LLM Leaderboard
π
14.2k
Track, rank and evaluate open LLMs and chatbots
Following
-
-
Playground V2.5
π1.15kGenerate highly aesthetic images
-
Video Object Detection
π·209Real-time object detection w/ π€ Transformers.js
-
abacusai/Smaug-72B-v0.1
Text Generation β’ 72B β’ Updated β’ 9.24k β’ 468 -
AI Comic Factory
π©11.3kCreate your own AI comic with a single prompt
-
moondream2
π445a tiny vision language model
-
Real-Time Text-to-Image SDXL Lightning
β‘623Real-Time Image Generation with SDXL Lightning
-
PhotoMaker
π·1.96kGenerate personalized realistic photos of a person from images
-
PDF Chatbot
π382Ask questions about PDFs using a chatbot
-
MagicAnimate
π1.42kGenerate animated videos from images and motion sequences
-
CLIP Interrogator
π΅2.99kGenerate detailed prompts from an image
-
InstantX/InstantID
Text-to-Image β’ Updated β’ 82.5k β’ 895 -
Soft Video Understanding
π64 -
VideoMamba
π97Identify actions and objects in videos and images
-
Can You Run It? LLM version
π1.05kCheck GPU requirements for running LLMs
-
Guardrails Arena
β63Jailbreak the LLM and privacy guardrails
-
DynamiCrafter
π¨165Animate a photo into a short video with a custom prompt
-
IDM VTON
π2.14kHigh-fidelity Virtual Try-on
-
OpenVoiceV2
π€364Clone a voice and generate speech from text
-
QR Code AI Art Generator
π±2.01kQR Code AI Art Generator Blend QR codes with AI Art
-
JARVIS
π₯293Voice Chat with JARVIS
-
DALLE 3 XL v2
π₯1.79kGenerate highβresolution images from your text prompt
-
One Step SDXL Comparison
π¦Ά133Compare models that generate images ultra fast in 1 step
-
PuLID
β‘540Generate personalized images preserving a face identity
-
InstantStyle + Hyper SD
πΌ30Text-to-Image InstantStyle with Hyper SD
-
β Zero GPU Spaces β
β‘985List of spaces using ZERO-GPU
-
Enhance This HiDiffusion SDXL
π411Creative Upscaler High-Res Image Generation HiDiffusion SDXL
-
SDXL Flash
β‘321High quality image generation in 3 second
-
Chattts Zero
π’336Generate audio from text with tuning options
-
GLiNER HandyLab
β‘91Perform multiple NLP tasks like NER, QA, and summarization
-
Florence 2
π848Generate captions, detections, and OCR from an image
-
Flash Lora
β‘157Generate custom images using LoRAβenhanced Stable Diffusion
-
Fake Insects
π127A game where you need to identify AI Generated insects
-
Whisper
π2.9kTranscribe audio files into written text
-
Voice Clone
π£2.71kGenerate voice-cloned audio from your text and voice sample
-
Indic Parler-TTS
π198A demo of Indic Parler-TTS
-
Qwen2.5 Coder Artifacts
π’276Generate HTML code from your app description
-
SexyImages
π439Sexy x6 Images Generator
-
LatentSync
π632Audio Conditioned LipSync with Latent Diffusion Models
-
Voice Cloning
β‘544Clone a voice and generate speech
-
XTTS
πΈ2.76kGenerate speech from text using a reference voice
-
PTA 1
π18Controlling Computers with Small Models
-
Llama 3.2 Reasoning WebGPU
π§231Small and powerful reasoning LLM that runs in your browser
-
Whisper JAX
π145Transcribe or translate audio from microphone, file, or YouTube
-
Magic Face
π€ͺ333Transform Your Face Into Legendary Characters!
-
Think in Sync
π§246An addictive AI-powered word puzzle.
-
Hunyuan3D-2.0
π3.44kText-to-3D and Image-to-3D Generation
-
F5-TTS
π£2.93kF5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
-
Skyreels A1 Talking Head
π»200Audio to Talking Face
-
Orpheus TTS
π250Try Orpheus TTS here
-
InfiniteYou-FLUX
πΈ1.1kFlexible Photo Recrafting While Preserving Your Identity
-
EasyControl Ghibli
π¦1.45kNew Ghibli EasyControl model is now released!!
-
DeepSite Gallery
π942Browse apps made with DeepSite
-
SmolVLM realtime WebGPU
β‘160Ask questions about your live camera view
-
Wan2.1 Fast
π₯1.63kCreate a short video from an image using a text prompt
-
ShallowCodeResearch
π51Coding research assistant that generates code and tests it
-
BAGEL
π222Demo for BAGEL
-
Qwen Image Edit
β874Edit images with AI using natural language prompts
-
Qwen Image Fast
πΌ155Generate images in 8-steps
-
FastVLM WebGPU
π450Real-time video captioning powered by FastVLM
-
Maya1
π116Demo of our new open source model maya1
-
Ringg Squirrel TTS V1.0
πΏ82Generate audio from text using voice selection
-
Z Image Turbo
π1.94kGenerate detailed images from your text prompts
-
Murder.Ai - LLMs that kill, lie, decieve
π΅60Even AI has something to hide
-
Pocket TTS ONNX Web Demo
π83Multilingual Pocket TTS voice cloning in the browser (CPU)
-
abenzerps/Qwen-Image-2.1-Turbo-Quantized
Text-to-Image β’ 7B β’ Updated β’ 112k β’ 5.77k