saddam213/AmuseAI
Local AI image, video, audio and text.
What it solves
Amuse provides a unified local interface for running a wide variety of AI generation tasks, including image, video, audio, and text processing, without needing to manage separate tools for each modality.
How it works
Built on .NET 10, the application acts as a central hub that supports multiple model formats like Safetensors, GGUF, and ONNX. It leverages different GPU backends—specifically CUDA for NVIDIA hardware and Vulkan for cross-vendor compatibility—to accelerate inference for various pipelines, including popular models like Stable Diffusion, FLUX, Qwen, and Whisper.
Who it’s for
This project is for users who want to run advanced generative AI models locally on their own hardware and require a comprehensive media-focused suite that includes editing, upscaling, and organization tools.
Highlights
- Supports diverse media generation including image, video, audio, and text.
- Includes built-in media editing tools like upscaling, inpainting, and video interpolation.
- Offers broad hardware support via CUDA and Vulkan backends.
- Compatible with a wide range of model architectures including Lora and ControlNet for fine-tuned output control.
Related
- Project
- Project
- Project
- Project
- Project