OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Open Generative AI

Open Generative AI is an open-source JavaScript application for generating AI images and videos, with image-to-video and audio-driven lip-sync workflows. It is powered by MuAPI and is described as available through a browser-hosted studio or a desktop app; the desktop app also documents local inference options.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Open Generative AI — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a single creative interface for several documented image, video and lip-sync workflows, or when you want to investigate desktop-based local inference.

Who it is for

  • Creators exploring image and video generation across multiple models.
  • Desktop users who want to configure local image inference or install a separate local engine for supported video workflows.

Documented uses

  • Generate images from text prompts or transform an image.
  • Create videos from text prompts or input images.
  • Make lip-sync clips driven by audio.
Before you choose

Requirements & limits

The README describes a hosted browser version that requires a free account to start generating, and desktop downloads. The repository lists an MIT license. Local inference is documented for the desktop app.

  • MuAPI powers the studio, while local inference is a separate desktop-app capability.
  • The bundled sd.cpp engine is documented for image models; Wan2GP is a user-installed option for specified video and larger image-model workflows.
  • Wan2GP requires Python and PyTorch with a CUDA- or ROCm-capable GPU on the machine running it.
  • The project documents platform-specific installation hurdles, including macOS Gatekeeper prompts and Ubuntu AppArmor considerations.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Configure local image inference in the desktop app

Set up the documented bundled sd.cpp engine for local image-model use.

Before you start

  • The Open Generative AI desktop app.
  • A compatible local machine; the documentation notes Metal GPU support on Apple Silicon and CUDA, Vulkan or ROCm on Linux and Windows.

Steps

  1. Open the desktop app.

  2. Go to Settings → Local Models.

  3. Configure the bundled sd.cpp engine and select a documented image model.

Expected outcome

The desktop app is configured to use its bundled local image-inference engine.

Guide limitations

  • This guidance covers engine configuration, not a complete generation walkthrough.
  • The documentation notes that Z-Image models can be memory-intensive.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
Anil-matcha/Open-Generative-AI · Official homepage title · retained in its source language
How we review sourcesSuggest a correction