ShiftHackZ/Stable-Diffusion-KMP

Stable Diffusion AI client app for Android and iOS

What it solves

SDAI is a cross-platform mobile client that provides a unified workflow for generating AI images. It eliminates the need to switch between different apps or web interfaces when using various Stable Diffusion backends, whether they are self-hosted servers, hosted APIs, or on-device local generation.

How it works

The app acts as a frontend that connects to a wide variety of providers. It supports remote backends like AUTOMATIC1111, SwarmUI, AI Horde, Hugging Face, OpenAI, Stability AI, Fal.ai, and ArliAI. For local generation, it integrates multiple runtimes including Microsoft ONNX, Google AI MediaPipe, stable-diffusion.cpp (for SDXL), Core ML (iOS), and PrismML Bonsai.

Who it’s for

Mobile users who want a professional-grade Stable Diffusion experience on Android and iOS, including those who run their own servers or prefer the privacy and offline capability of on-device generation.

Highlights

  • Multi-Backend Support: Connects to self-hosted servers (A1111, SwarmUI) and numerous cloud APIs.
  • On-Device Generation: Supports local inference on Android and iOS using various optimized runtimes.
  • Advanced Controls: Provides access to prompts, negative prompts, seed, CFG scale, LoRA, and embeddings where supported by the provider.
  • Privacy-Focused: Open-source with no ads or telemetry.
  • Built-in Tools: Includes an on-device benchmark to check hardware suitability for local runs and a local gallery for managing creations.

Related

  • Project
    easydiffusion/easydiffusion

    A one-click installer and user interface for Stable Diffusion that allows users to run powerful image generation AI locally without requiring technical knowledge.

  • Project
    vladmandic/sdnext

    A comprehensive web interface for AI image and video generation based on Stable Diffusion, featuring advanced memory optimizations and broad hardware support.

  • Project
    Sygil-Dev/sygil-webui

    A web-based user interface for Stable Diffusion that provides tools for image generation, upscaling, and prompt engineering with optimizations for low-VRAM GPUs.

  • Project
    xororz/local-dream

    An Android application that enables local Stable Diffusion image generation with hardware acceleration for Snapdragon NPUs.

  • Project
    Windsander/ADI-Stable-Diffusion

    A C++ library and CLI tool that enables high-performance, Python-free inference for Stable Diffusion models using ONNXRuntime across multiple platforms.