MFLUX-WEBUI using MLX and the FLUX DEV and Schnell models

A Pinokio application to manage ComfyUI environments with Docker.

Creative Image Enhancer/Upscaler. Powered By Refiners. 8GB VRAM | 10GB Install

One-click installer and dashboard for https://github.com/oobabooga/text-generation-webui

(NVIDIA) FramePack is a next-frame (next-frame-section) prediction neural network structure that generates videos progressively.

This is a Gradio web application that uses NVIDIA's Parakeet-TDT-0.6b model for automatic speech recognition with timestamp functionality.

[NVIDIA ONLY] "Stable Video Matting with Consistent Memory Propagation" 9GB install, 9GB+ VRAM

gradio ui for new higgs audio with low vram support and long text genration and 4bit 6 bit and 8 bit quantization option to run on low vram

chatterbox dubbing with gemini

This project provides a Gradio-based interface for interacting with the Ovis2-8B model. The script allows users to load the model, process image and video inputs, and generate text-based responses using a conversational chatbot.

A powerful web application that allows you to expand the boundaries of your images with AI-generated content, creating seamless extensions that match the original image style and context.

(NVIDIA ONLY) Welcome to Kokoro, a high-quality text-to-speech synthesis program powered by deep learning. This tool converts any text into high-fidelity speech in just a few seconds. Simply input text, select a voice, adjust the speed, and enjoy the generated audio.

[Windows] and [NVIDIA] Spark-TTS is a high-quality text-to-speech synthesis system that enables voice cloning and speech generation using deep learning models. The system allows users to generate speech with customizable parameters such as pitch, speed, and gender.

BEN2 Background Remover is an AI-powered tool designed to remove backgrounds from images with high precision. It utilizes the BEN_Base model for processing images and is implemented using Gradio for an interactive web-based interface.

Image Upscale is an AI-powered application designed to enhance and upscale images using advanced techniques like Stable Diffusion and Tile ControlNet. It provides high-quality image enhancement with options for HDR effects and customizable settings.

KittenTTS is an ultra-lightweight, CPU-friendly text-to-speech model with 15M params for real-time, high-quality voices. Open source, fast start. 😺

Florence-2 is a large vision-language model capable of various image and text generation tasks, such as object detection, captioning, and grounding. This demo allows users to interact with these capabilities by uploading images and selecting from various tasks.

A powerful, AI-powered Gradio application for downloading, transcribing, and analyzing YouTube videos and audio.

High-Quality Text-to-Speech for Indian Languages

Pinokio installer for Illusion Diffusion HQ