Open LLM Leaderboard
Track, rank and evaluate open LLMs and chatbots
Track, rank and evaluate open LLMs and chatbots
Generate highly aesthetic images
Real-time object detection w/ π€ Transformers.js
Create your own AI comic with a single prompt
a tiny vision language model
Real-Time Image Generation with SDXL Lightning
Generate personalized photos of a person from a prompt
Ask questions about PDFs using a chatbot
Generate animated videos from images and motion sequences
Generate detailed prompts from any image
Identify actions and objects in videos and images
Check if your GPU can run a chosen LLM model
Jailbreak the LLM and privacy guardrails
Animate a photo into a short video with a custom prompt
High-fidelity Virtual Try-on
Generate speech in a target voice from a short audio clip
QR Code AI Art Generator Blend QR codes with AI Art
Voice Chat with JARVIS
Generate highβresolution images from your text prompt
Compare models that generate images ultra fast in 1 step
Generate personalized images preserving a face identity
Text-to-Image InstantStyle with Hyper SD
List of spaces using ZERO-GPU
Creative Upscaler High-Res Image Generation HiDiffusion SDXL
High quality image generation in 3 second
Generate audio from text with tuning options
Perform multiple NLP tasks like NER, QA, and summarization
Generate realistic talking heads from image+audio
Generate captions, detections, and segmentations from images
Generate custom images with LoRAβenhanced Stable Diffusion
A game where you need to identify AI Generated insects
Transcribe audio or YouTube video into text
Clone a voice and generate speech from text
A demo of Indic Parler-TTS
Generate and preview code from your app description
Sexy x6 Images Generator
Audio Conditioned LipSync with Latent Diffusion Models
Clone a voice and generate speech
Generate speech from text using a reference voice
Controlling Computers with Small Models
Small and powerful reasoning LLM that runs in your browser
Transcribe or translate audio from microphone, file, or YouTube
Transform Your Face Into Legendary Characters!
An addictive AI-powered word puzzle.
Text-to-3D and Image-to-3D Generation
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Audio to Talking Face
Try Orpheus TTS here
Flexible Photo Recrafting While Preserving Your Identity
New Ghibli EasyControl model is now released!!
Browse apps made with DeepSite
Ask questions about your webcam view and get text answers
Animate a still image into a short video using a prompt
Coding research assistant that generates code and tests it
Demo for BAGEL
Edit images using natural language instructions
Generate images in 8-steps
Real-time video captioning powered by FastVLM
Demo of our new open source model maya1
Generate audio from text using voice selection
Generate detailed images from your text prompts
Even AI has something to hide
Multilingual Pocket TTS voice cloning in the browser (CPU)