# mochidiffusion/mochidiffusion **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/mochidiffusion-mochidiffusion).** 7,840 stars · 361 forks · Swift · gpl-3.0 ## Links - GitHub: https://github.com/MochiDiffusion/MochiDiffusion - awesome-repositories: https://awesome-repositories.com/repository/mochidiffusion-mochidiffusion.md ## Topics `ane` `apple` `apple-silicon` `coreml` `macos` `neural-engine` `stable-diffusion` `swift` `swiftui` ## Description MochiDiffusion is a local client for Stable Diffusion that functions as an AI image generation studio. It provides a workspace for performing text-to-image, image-to-image, and inpainting tasks, enabling the production of high-resolution images offline using local hardware and neural engine acceleration. The project includes a local model manager for importing, organizing, and converting machine learning models into compatible formats for offline execution. It features a ControlNet integration tool to guide structural composition and spatial layout, alongside a dedicated image upscaler that uses super-resolution algorithms to increase image dimensions and fine detail. The application covers a broad capability surface including image refinement through multi-stage processing, metadata embedding for persisting prompts in EXIF fields, and generative media asset management via a searchable gallery. It also incorporates a safety-checker for content filtering and a background task queue to manage compute-heavy generation requests. ## Tags ### Artificial Intelligence & ML - [Image Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation.md) — Implements a local client for generating high-resolution images offline using local hardware and neural engines. ([source](https://github.com/MochiDiffusion/MochiDiffusion#readme)) - [Local Diffusion Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/local-diffusion-interfaces.md) — Provides a desktop application for executing diffusion models on local hardware for offline image generation. - [AI Generation Studios](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-generation-studios.md) — Provides a creative workspace for text-to-image, image-to-image, and inpainting with integrated model management. - [Custom Model Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-model-integrations.md) — Provides interfaces for importing and organizing user-defined machine learning models. - [Image Inpainting](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-pipelines/text-to-image-generators/image-inpainting.md) — Modifies specific image regions by combining masks with generative models for targeted editing. - [Image-to-Image Diffusion Toolkits](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-pipelines/text-to-image-generators/image-inpainting/image-to-image-diffusion-toolkits.md) — Enables the use of starting images as structural guides to modify existing visuals or create new ones. ([source](https://github.com/MochiDiffusion/MochiDiffusion/blob/main/CHANGELOG.md)) - [Local Model Management](https://awesome-repositories.com/f/artificial-intelligence-ml/local-model-management.md) — Provides tools for importing, organizing, and converting models for offline local execution. - [Hardware-Accelerated](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/hardware-and-acceleration/tensor-computing-libraries/tensor-libraries/hardware-accelerated.md) — Optimizes inference speed by routing tensors through dedicated on-device neural processors. - [Spatial Control Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training-interfaces/spatial-control-interfaces.md) — Provides a graphical interface to guide the structural composition and spatial layout of images. - [Spatial Conditioning Controllers](https://awesome-repositories.com/f/artificial-intelligence-ml/spatial-processing-operations/spatial-processing-operations/spatial-conditioning-controllers.md) — Provides spatial conditioning to constrain the layout and structural composition of generated images. - [Generative Upscalers](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-upscalers.md) — Uses generative techniques to reconstruct high-resolution details and increase image dimensions. - [Multi-Pass Refinement](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-upscalers/multi-pass-refinement.md) — Uses a specialized refiner model to perform subsequent sampling passes for improved fine detail. ([source](https://github.com/MochiDiffusion/MochiDiffusion/blob/main/CHANGELOG.md)) - [Image Super Resolution Models](https://awesome-repositories.com/f/artificial-intelligence-ml/image-super-resolution-models.md) — Increases image dimensions and recovers fine detail using super-resolution algorithms. - [Model Repository Organization](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/model-architecture-evaluation/model-repositories/model-repository-organization.md) — Organizes external model files within local filesystem paths to manage different generation styles. ([source](https://github.com/MochiDiffusion/MochiDiffusion/blob/main/README.md)) - [Hardware Acceleration](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/hardware-and-acceleration/hardware-acceleration.md) — Allows selecting between CPU, GPU, and Neural Engine compute units to optimize generation speed. ([source](https://github.com/MochiDiffusion/MochiDiffusion/blob/main/CHANGELOG.md)) - [Model Conversion Utilities](https://awesome-repositories.com/f/artificial-intelligence-ml/model-conversion-utilities.md) — Provides utilities to convert machine learning models into formats compatible with local offline execution. ([source](https://github.com/MochiDiffusion/MochiDiffusion/wiki/How-to-convert-Stable-Diffusion-models-to-Core-ML)) - [Multi-Stage Refinement](https://awesome-repositories.com/f/artificial-intelligence-ml/video-generation/multi-stage-refinement.md) — Improves image quality by applying a second diffusion pass using a specialized refiner model. ### Part of an Awesome List - [Spatial Guidance Controls](https://awesome-repositories.com/f/awesome-lists/ai/image-editing-and-manipulation/spatial-guidance-controls.md) — Guides the structural layout and composition of generated images using spatial constraints. ### Data & Databases - [Local Model Loading](https://awesome-repositories.com/f/data-databases/local-model-loading.md) — Loads machine learning weights by scanning local filesystem paths for compatible model files. ### Graphics & Multimedia - [AI Upscaling](https://awesome-repositories.com/f/graphics-multimedia/image-editing-processing/image-enhancement-tools/ai-upscaling.md) — Enhances generated images through AI-driven upscaling and fine detail refinement.