Amuse is a high-performance local .NET application for AI image and video generation. Create and process media with a streamlined interface designed for ease of use and seamless integration with modern hardware.
- Automatic installation of an isolated, Python environment.
- Safetensors, GGUF, and ONNX support.
- Video Editor for generated or local content.
- Image/Video Upscale for static and moving media.
- Feature Extraction from images and video.
- Video Interpolation for frame rates and slow-motion.
- Image Inpaint to remove objects or fill areas.
- Advanced Image Editing with selection and masking tools.
- Voice Generation (Supertonic).
- Speech Recognition (Whisper).
- Media Gallery for organization and management.
- Lora/ControlNet Support for output control.
- Z-Image
- Qwen
- FLUX.1
- FLUX.2
- Chroma
- Kandinsky5
- StableDiffusion-XL
- StableDiffusion-3
- LTX
- LTX-2
- Wan 2.2
- CogVideoX
- Kandinsky5
- SkyReels-V2
- Helios
- ACE-Step XL
- Whisper
- Supertonic
Amuse utilizes NVIDIA CUDA 12.8 and AMD ROCm 7.2 for local hardware acceleration.
Amuse leverages CUDA 12.8, providing native support for the latest generation of hardware.
While legacy architectures (Pascal/Maxwell) are technically supported, an RTX-enabled card is strongly recommended to utilize Tensor Cores for efficient generation speeds.
| Architecture | Platform Support | GPU Models |
|---|---|---|
| Blackwell (SM_100) | Windows 10, 11, Server 22 | GeForce RTX 5090, 5080, 5070 Ti, 5070; RTX PRO Blackwell series |
| Ada Lovelace (SM_89) | Windows 10, 11, Server 22 | GeForce RTX 4090, 4080, 4070 Ti/Super, 4070, 4060 Ti, 4060; RTX 6000/5000/4000 Ada |
| Ampere (SM_86) | Windows 10, 11, Server 22 | GeForce RTX 3090 Ti, 3090, 3080 Ti, 3080, 3070 Ti, 3070, 3060 Ti, 3060; RTX A-series (A6000, etc.) |
| Turing (SM_75) | Windows 10, 11, Server 22 | GeForce RTX 2080 Ti, 2080 Super, 2070, 2060; GTX 1660 Ti, 1660 Super, 1650 |
Note: Minimum Driver (NVIDIA):
Version 527.41or later is required forCUDA 12.8compatibility.
Amuse leverages ROCm 7.2, which introduces a unified software stack for Windows and Linux.
This version is highly optimized for RDNA 3 and the newly released RDNA 4 architectures, offering significant performance gains in local AI inference.
| Architecture | Platform Support | GPU Models |
|---|---|---|
| gfx1151 (STX_Halo) | Windows 10, 11, Server 22 | Ryzen AI MAX+ Pro 395 |
| gfx110X (RDNA3) | Windows 10, 11, Server 22 | Radeon PRO W7900/W7800/W7700/V710, RX 7900 XTX/XT/GRE, RX 7800 XT, RX 7700 XT |
Note: Minimum Driver (AMD):
Version 26.1.1or later is required forROCM 7.2compatibility.
