Swap faces in images and enhance them

Search for answers using OpenAI's language models

Extract text from images in multiple languages

Evaluating LMMs on Japanese subjects

Genshin Impact Game Style Music Generator

Play Truck Town

Run benchmarks on prediction models

View and submit language model evaluations

Enhance and analyze audio by reducing noise and detecting plosives

Reconstruct and convert voice audio

Remove backgrounds from images

Generate copyright-free anime images

Clone a voice with text input

Monitor application health

Clean and restore noisy document images

Generate sound for silent videos

Create albedo, shading, and diffuse images from a single photo

Translation using the SalamandraTA 2B model

Generate a video from text prompts

Convert vocals with pitch adjustment