Skip to content

README.md

Latest commit

 

History

History
116 lines (102 loc) · 3.41 KB

README.md

File metadata and controls

116 lines (102 loc) · 3.41 KB
Raw

Amuse

Amuse is the flagship demo application for the TensorStack SDK, showcasing high-performance local AI image, video, audio and text generation through a modern, extensible .NET architecture.

Features

  • 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.

Image Pipelines

  • Z-Image
  • Qwen
  • FLUX.1
  • FLUX.2
  • Chroma
  • Kandinsky5
  • StableDiffusion-XL
  • StableDiffusion-3
  • Ernie Image
  • Anima
  • JoyAI Image
  • PRX-Pixel
  • Krea2
  • GLM Image

Video Pipelines

  • LTX
  • LTX-2
  • Wan 2.2
  • CogVideoX
  • Kandinsky5
  • SkyReels-V2
  • Helios
  • Motif
  • AnyFlow

Audio Pipelines

  • ACE-Step
  • ACE-Step XL
  • Whisper
  • Supertonic v3
  • LongCat Audio

Text Pipelines

  • Qwen 3.0
  • Qwen 3.5
  • Qwen 3.6
  • Gemma 4.0

GPU Support

Amuse leverages CUDA 13.0, 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
Windows 11*
Server 2022		 GeForce RTX 5090, 5080, 5070 Ti, 5070;
RTX PRO Blackwell series
Ada Lovelace
(SM_89)		 Windows 10
Windows 11*
Server 2022		 GeForce RTX 4090, 4080, 4070 Ti/Super, 4070, 4060 Ti, 4060;
RTX 6000/5000/4000 Ada
Ampere
(SM_86)		 Windows 10
Windows 11*
Server 2022		 GeForce RTX 3090 Ti, 3090, 3080 Ti, 3080, 3070 Ti, 3070, 3060 Ti, 3060;
RTX A-series (A6000, etc.)
Turing
(SM_75)		 Windows 10
Windows 11*
Server 2022		 GeForce RTX 2080 Ti, 2080 Super, 2070, 2060;
GTX 1660 Ti, 1660 Super, 1650

Note: Minimum Driver (NVIDIA): Version 580.65 or later is required for CUDA 13.0 compatibility.

** Windows 11 users may need to Run As Administrator during environment creation if there are failures.

External Dependencies