saddam213/AmuseAI

Local AI image, video, audio and text.

What it solves

Amuse provides a unified local interface for generating and editing AI-driven media, eliminating the need to manage multiple separate tools for image, video, audio, and text generation.

How it works

Built on .NET 10, the application integrates various AI pipelines (such as FLUX, StableDiffusion, Qwen, and Whisper) and supports multiple GPU backends including CUDA for Nvidia and Vulkan for cross-vendor compatibility (AMD, Nvidia, Intel). It supports various model formats including Safetensors, GGUF, and ONNX.

Who it’s for

Users who want to run a comprehensive suite of generative AI tools locally on their own hardware across different GPU brands.

Highlights

  • Multimodal Generation: Supports a wide array of pipelines for images, video, audio, and text.
  • Advanced Media Tools: Includes a built-in video editor, image/video upscaling, inpainting, and interpolation.
  • Hardware Flexibility: Compatible with Nvidia (CUDA) and other GPUs via Vulkan.
  • Control Tools: Supports Lora and ControlNet for precise output steering.

Related

  • Project
    v-modal/vmodal_sdk_android

    V‑Modal AI Android SDK – a native Kotlin/Java library that lets Android apps upload videos/images, have them indexed by V‑Modal’s cloud AI, and perform semantic search across the media. The SDK handles authentication, signed streaming uploads, progress/cancellation, and returns typed results, leaving all UI design to the developer.

  • Project
    gokayfem/ComfyUI_VLM_nodes

    A production-oriented suite of ComfyUI nodes for vision-language models, providing structured detection, segmentation, and adaptive video reasoning with VRAM optimizations.

  • Project
    remyxai/VQASynth

    A pipeline for transforming image datasets into spatial VQA datasets to improve the 3D spatial reasoning and distance estimation capabilities of Vision-Language Models.

  • Project
    lycohana/BiliSum

    BiliSum is a video-to-knowledge tool that converts Bilibili, YouTube, and local videos into transcriptions, visual notes, and a local RAG-powered knowledge base.