Anil-matcha/Open-Generative-AI

Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 600+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.

What it solves

Open Generative AI is a free, open-source alternative to commercial AI image and video platforms. It tackles problems like subscription fees, content filters, and vendor lock-in by giving you an unrestricted, self-hostable studio that works with many models — no prompts rejected, no guardrails.

How it works

The app connects to the MuAPI cloud service for hosted model access, and also supports local inference through two optional engines: sd.cpp (a bundled C++ engine for image models) and Wan2GP (a separately installed Python tool for video and large image models). You pick a studio (Image, Video, Audio, Lip Sync, etc.), choose a model from 200+ options, and optionally toggles to local mode for offline generation. All local installs run on your own machine; the hosted web version always uses cloud APIs.

Who it’s for

Creators, developers, and small teams who want full control over AI media generation without paying per-month subscriptions or being subject to platform restrictions. It’s also aimed at builders who want to white-label the app into their own branded AI studio for reselling.

Highlights

  • No content filters, prompt rejections, or guardrails
  • 600+ models across 14 studios (image, video, audio, lip sync, cinema, and more)
  • Local inference with sd.cpp (Mac/Windows/Linux) and Wan2GP (CUDA/ROCm GPU) for offline use
  • Multi-image input up to 14 reference images for edit models
  • Desktop apps for macOS, Windows, and Linux, plus a hosted web version
  • Extensible UI and support for adding custom models
  • White-label option to launch your own branded studio

Related

  • Project
    wide-trace/open-higgsfield

    An open-source image and video generation studio that lets users access 38 different AI models using their own API keys to avoid vendor lock-in.

  • Project
    lidge-ai/ima2-gen

    A local-first visual generation studio that consolidates image and video workflows from multiple AI providers into a single interface with local storage and agent-friendly CLI tools.

  • Project
    GoogleCloudPlatform/genmedia-creative-studio

    A web application for creative exploration that integrates Google Cloud's generative media models for image, video, music, and speech generation.

  • Project
    waooAI/waoowaoo

    An AI creative workspace for images and videos that combines an AI assistant, a visual canvas for organization, and integration with various generative models.

  • Project
    hero8152/Infinite-Canvas

    A visual, infinite canvas workspace that integrates multiple AI APIs and local ComfyUI workflows for collaborative generative AI content creation.