A Mac programme called Diffusers can make graphics from written descriptions of what you want to create. It makes advantage of cutting-edge models contributed to the Hugging Face Hub, and for best efficiency, it is optimised and converted to Core ML.
There are five models of diffusers: OFA tiny v0, Stable Diffusion 1.4, Stable Diffusion 1.5, Stable Diffusion 2, and Stable Diffusion 2.1. Users can select the model that best meets their needs because each one has its own personality and sense of style.
Users of the application can modify the generation parameters to aid in producing the desired image. The model to employ, the prompt, the negative prompt, the seed, and the steps are some of these.
The positive prompt is what you don’t want, and the prompt is what you describe as what you want. While the steps determine how many diffusion stages the image generation will undergo, the seed enables for the replication of a prior generation.
Diffusers does not gather any data and is privacy-focused. It also has a permissive licence and is open source. It is currently being developed for iOS/iPadOS support and is free to use.