Open ASR Leaderboard
Request evaluation for a speech model
Request evaluation for a speech model
Radiology Image & Report Explainer Demo. Built with MedGemma
Generate app code using descriptions
Fast and free uncensored chatbot that just works.
VGGT (CVPR 2025)
An interactive view of human heart
Wan2.1-T2V-14B + Fast 4-step with NAG + Automatic Audio
Create personalized speech using text and audio samples
Uncensored General Intelligence Leaderboard
Start a chat to get answers and explanations from a language model
Swap faces in images and enhance them if desired
Chat with images, videos, or PDFs to generate text
Apply the motion of a video on a portrait
Wan: Open and Advanced Large-Scale Video Generative Models
Audio-Driven Multi-Person Conversational Video Generation
Generate images from text descriptions
Create AI-powered datasets
Transform flat-lay shots into on-model photos
Describe images, videos, and audio
Add objects to images using prompts
Create and quantize Hugging Face models
Create images of a given character in different poses
Easily expand image boundaries
Upscale an image to higher resolution