Janus Pro 7B is a powerful multimodal AI model designed for advanced image understanding and text-to-image generation.

Arbitrary-steps Image Super-resolution via Diffusion Inversion

Separate Anything You Describe (https://huggingface.co/spaces/Audio-AGI/AudioSep)

Next generation face swapper and enhancer

A one-click installer for setting up RFdiffusion using Pinokio.

[WINDOWS/LINUX ONLY] Easily train a good VC model with voice data <= 10 mins!: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Advanced RVC Inference for quicker and effortless model downloads.

A local implementation of the Kokoro Text-to-Speech model

Clone de voz multilíngue usando Coqui TTS

TANGO - Task-oriented AgeNt with GPT-4 for Online task solving

Uncensored Deepfakes for images and videos without training and an easy-to-use GUI.