Display LLM benchmark leaderboard and info

Rename models in dataset leaderboard

Generate detailed pose estimates from images

Watermark detection

Generate images from text prompts

Download YouTube videos or audio

Convert (almost) everything to PDF!

Describe a medical image in text

Persian Text Embedding Benchmark

Turn images into detailed face masks

Use AI to Change Clothing

Generate responses to text prompts using LLM

Generate various types of text and insights

Audio Conditioned LipSync with Latent Diffusion Models

Display CLIP benchmark results for inference performance

Upscale images to x4

Convert images to text using OCR

Analysis of data on an invoice

Display EMNLP 2022 papers on an interactive map

Generate answers by describing an image and asking a question