Open Generative AI
An open-source AI image and video studio with local desktop generation on macOS, Windows and Linux, plus support for your own Wan2GP server.
Alternative to:
Open Generative AI is an AI image and video studio for creators who want to generate media on their own hardware. Local inference is available only in the desktop app.
- Local image generation: Run SD 1.5, SDXL and Z-Image through stable-diffusion.cpp without an API key.
- Video and larger image models: Use your own Wan2GP installation on the same machine or a remote server for Flux, Qwen-Image, Wan, Hunyuan and LTX-2.
- Image editing and animation: Edit images with multiple references when the selected model supports them, or generate videos from text and starting images.
- Audio and clipping: Generate or edit audio and music from text prompts, and extract highlights from longer videos.
The desktop app runs on Intel and Apple Silicon Macs, Windows and Ubuntu Linux. The software is free and open source under the MIT license.
The stable-diffusion.cpp engine supports CPU inference on all platforms, Metal on Apple Silicon, and CUDA, Vulkan or ROCm on Windows and Linux. Wan2GP requires an NVIDIA or AMD GPU on the machine running it, even if the desktop interface runs on a Mac. For Z-Image, 16 GB RAM is recommended; it can hang an 8 GB Apple Silicon Mac.
