Anil-matcha/Open-Generative-AI

Project overview

A free, open-source, self-hostable generative AI studio for creating images, video, and audio using 200+ models without built-in content filters or subscription fees. Local inference is limited to the desktop application and requires sufficient system memory for certain models.

Project type

Workflow · Image & Vision · Video

Use cases

Image Processing · Video Creation · Audio & Speech

Deployment

Refer to project documentation

License

MIT

Best for

• Creators and general users seeking a self-hostable or local generation tool without built-in content moderation.
• Users requiring multi-image input for image editing models.

Key capabilities

• Generate images from text prompts (50+ models) or transform existing images (55+ models) with multi-image input support.
• Generate videos from text prompts (40+ models) or animate a start-frame image (60+ models).
• Animate portrait images or sync lips on existing videos using audio with 9 dedicated models.
• Interface for photorealistic cinematic shots with pro camera controls (Lens, Focal Length, Aperture).
• Build and run multi-step AI pipelines visually with a node-based editor and community templates.
• Run local model inference via bundled sd.cpp engine or by connecting to a remote Wan2GP server.
• Upload up to 14 reference images for compatible edit models with order badges and batch upload.

Limitations and risks

• Local inference is only available in the desktop app. The hosted web version always uses cloud APIs.
• On a base 8 GB M-series Mac, Z-Image is known to hang the system. 16 GB RAM is recommended for sd.cpp Z-Image.
• The macOS app is not notarized by Apple and requires bypassing Gatekeeper.
• The Windows installer is not code-signed and triggers SmartScreen warnings.
• The application intentionally has no content filters, nanny guardrails, or prompt rejections.

Getting started

• Download the installer for your OS from the releases page, install, and launch the application. The process does not require Node.js or a terminal. Alternatively, use the hosted web version requiring no installation.

Evidence and sources

• GitHub project description: Free AI image & video generation studio with 200+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.
• README: The free, open-source alternative to AI Video Platforms. Generate AI images and videos using 200+ state-of-the-art models — no content filters, no closed ecosystem, no subscriptio…
• README: Why Open Generative AI instead of other AI Video Platforms? - **No filters** — no content filters, no nanny guardrails, no prompt rejections - **Free & open-source** — no subscrip…
• README: One-click installers — no Node.js or terminal required.
• README: Windows SmartScreen may show a warning because the installer is not code-signed:

Reviewed at: 2026-07-17T10:46:50Z