Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio

Modification of the KSampler for running models like Wan2.2 a14B

A ComfyUI custom node integration for multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, IndexTTS-2, Chatterbox (classic and multilingual 23-lang), F5-TTS, Higgs Audio …

An interactive image adjustment node for ComfyUI, with an easy-to-use graphical interface and realtime preview.

This repository is dedicated to maintaining, updating, fixing bugs and keeping up to date my inpainting ComfyUI workflow, previously hosted on CivitAI called: Proper Flux Control-Net inpainting and…

Separate stems (vocals, bass, drums, other) from audio. Recombine, tempo match, slice/crop audio

Converts pixel-art-style images such as those from generative models or low-quality sprites to true resolution usable assets

This node preserves image quality by selectively merging only the changed regions from AI-generated edits back into the original image.

Media Player that can play multiple videos/images at once in sync. Easily drag and drop media to rearrange them on a grid.

Modified version of Chatterbox that accepts text files as input and no character restrictions. I use it to make audiobooks, especially for my kids.

This script filters a LoRA `.safetensors` file to keep only the U-Net weights, removing any text encoder weights.

An ComfyUI custom node integration for multi-language High-quality Text-to-Speech and Voice Conversion nodes using ResembleAI's Chatterbox TTS and F5-TTS with unlimited text length, SRT timing Char…

We achieves high-quality first-frame guided video editing given a reference image, while maintaining flexibility for incorporating additional reference conditions.

JoyCaption ComfyUI Nodes

ComfyUI nodes to crop before sampling and stitch back after sampling that speed up inpainting

ComfyUI canvas editor page

Vision inference with transformers

LoRA Manager for ComfyUI - A powerful extension for organizing, previewing, and integrating LoRA models with metadata and workflow support.

Save images with Civitai-compatible generation metadata in ComfyUI

Tag manager and captioner for image datasets

A tool to help adjust or zero-out Flux Block Weights and SAVE. I'm not a dev, so this implementation might be wrong.

just some logical processors

This is to help fix txt. file captions made with auto captioners that uses a lot of the own subject body position, that can be tricky for inference and training with models like Flux.

A custom node for ComfyUI that allows users to overlay text on images with support for custom fonts and style.

set prompt to divided region

This extension allows easy drag-and-drop of PNG files anywhere on the WebUI to quickly view image analysis in the PNG Info tab.

model merge extention for stable diffusion web ui