Wanted

Generates Minecraft skins with a text prompt using the HuggingFace "monadical-labs/minecraft-skin-generator" model.

This Gradio application demonstrates the capabilities of the "dots.ocr" model, a powerful multilingual document parser.

Slightly improved official version for finetune xtts

Framework for podcast creation with search grounded llms for script generation and open source tts libraries

Contribute to coqui-ai/xtts-streaming-server development by creating an account on GitHub.

AMD 0.9B efficient text to video diffusion model

Using RVC via console or python scripts

Implementation of F5-TTS in Swift using MLX

Fooocus web UI for Stable Diffusion

基於OpenVino-int8權重，精簡的QwenASR小工具，用於即時辨識以及字幕轉換使用

Auto detecting, masking and inpainting with detection model.

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

OBS Studio - Free and open source software for live streaming and screen recording

ComfyUI-Qwen3-TTS brings Alibaba's powerful Qwen3-TTS models to ComfyUI Multi-GPU Support: CUDA, Apple Silicon (MPS), Intel Arc (XPU), and CPU

Generative Models by Stability AI

Autotune Module for Python "PyAutoTune"

Contribute to ComposioHQ/open-genspark development by creating an account on GitHub.

A collection of utility nodes from the VNCCS project that are useful not only for the project's primary goals but also for everyday ComfyUI workflows.

2D Video to 3D Generator, Creating Side-By-Side (SBS) Videos easily

Utility for extracting prompt metadata from Civitai AI images, auto-downloading the associated resources, and outputting/formatting the prompt information.