Hanami Live TranslatorTranslation site

A multimodal AI with vision, capable of recognizing an image (like ChatGPT 4). Demo available on GitHub

A project that increases the quality and resolution of your videos via a prompt. Technique used: Temporal-Consistent Diffusion Model

Manipulate your images with ease using a text-based AI prompt. An AI that simultaneously uses StyleGAN and CLIP

Quickly create images of a character in different positions while maintaining consistency

Improve the quality and resolution of your images with an open-source tool. Models currently in use: RealCUGAN, RealESRGAN, Waifu2x and SRMD

A flexible speech recognition model that excels in multilingualism and translation. Ideal for a wide range of audio applications