Wanted

Optimized for 8Gb inference LTX-2 audio–video generative model. + Web UI. Model created by:

Stable Diffusion web UI

Seedance 2.0 is a revolutionary multi-modal video generation model that bridges the gap between AI and professional filmmaking. This repository provides the official Python client for interacting with the Seedance API.

X2SAM: Any Segmentation in Images and Videos

High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

Contribute to FranciscooGarciaa/Cuantico development by creating an account on GitHub.

CosyVoice2 功能扩充（预训练音色推理/3s极速复刻/自然语言控制/自动识别/音色模型保存/API）

State of the art OSINT tool. | A powerful open-source alternative to other face search engines.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Forge for stable-diffusion-webui-amdgpu (formerly stable-diffusion-webui-directml)

ComfyUI Installation Guide for Pinocchio OS: This repo offers a step-by-step tutorial for installing ComfyUI on Pinocchio OS, including screenshots and instructions. It covers downloading the OS, installing ComfyUI, setting up dependencies like CUDA, and testing the installation. Contributions are welcome!

High performance self-hosted photo and video management solution.

Pipelines: Versatile, UI-Agnostic OpenAI-Compatible Plugin Framework

Open source alternative to NotebookLM for teams. Join our Discord: https://discord.gg/ejRNvftDp9

Official inference repo for FLUX.1 models

Effort free video editing!

A wav2lip Web UI using Gradio

Inference Specialization

FOSS Image background remover with 10 open source rmbg models

🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.