Amuse
Local AI creation app for Windows with image, video, audio and text models, GGUF and ONNX support, and acceleration for NVIDIA, AMD and Intel GPUs.
Amuse combines AI generation with media editing in a Windows app that runs models on your own hardware. It's for people who want to create images, video, audio and text locally, then work on the results in the same application. Its editor also accepts existing local video.
Image tools include inpainting to remove objects or fill selected areas, plus selection and masking controls for more detailed edits. LoRA and ControlNet support give you additional control over generated output. Amuse can upscale images and video, interpolate video frames for higher frame rates or slow motion, and organize media in a gallery.
Model support spans several kinds of creative work. Image pipelines include FLUX.1, FLUX.2, Qwen and StableDiffusion-XL, while video options include Wan and CogVideoX. Supertonic handles voice generation, Whisper handles speech recognition, and audio pipelines include ACE-Step XL and LongCat Audio. Qwen and Gemma provide text generation. Amuse accepts Safetensors, GGUF and ONNX models.
GPU acceleration uses CUDA for NVIDIA hardware or Vulkan for compatible AMD, NVIDIA and Intel GPUs. NVIDIA RTX cards are recommended for generation performance; compatibility depends on the GPU, driver and backend.
The source code is open source under Apache 2.0. Compiled binaries use a separate Amuse 2.0 License because they bundle third-party software and dependencies.
