Diffusers is a Mac app that utilizes community-contributed models to generate images from text descriptions. Diffusers uses Core ML for optimal performance and privacy is ensured as no content leaves the user's computer. There are five models to choose from, each with their own personality and style, and users can tweak the generation settings to achieve desired results. Diffusers is fully open source and free to use.
- Diffusion Image Generation: Generate images from a text description of what you want using state-of-the-art models contributed by the community to the Hugging Face Hub, optimized and converted to Core ML for maximum performance.
- Privacy: The prompts and images are yours to use, and will never leave your computer (unless you choose to share them with friends or colleagues).
- Performance: Diffusers leverages the best technologies such as native Swift app designed for macOS, Core ML models optimized for CPU, GPU, and Apple Neural Engine, and Diffusers library from Hugging Face, ported to Swift for maximum performance.
- Model Selection: Launches with a set of 5 models, downloaded from the Hugging Face Hub: Stable Diffusion 1.4, Stable Diffusion 1.5, Stable Diffusion 2, Stable Diffusion 2.1, and OFA small v0.
- Generation Settings: Parameters such as model to use, prompt and negative prompt, guidance scale, seed, and steps can be controlled.
- Open Source: Diffusers is fully open source and has a permissive license that allows you to build on it to create your products.