aMUSEd is an open-source platform that provides various natural language processing (NLP) models, datasets, and tools. It includes aMUSEd, a lightweight masked image modeling (MIM) based on MUSE, for text-to-image generation. Compared to latent diffusion, MIM requires fewer inference steps and is more interpretable. Additionally, MIM can be fine-tuned with just one image to learn additional styles. aMUSEd provides checkpoints for both models, allowing for direct generation of images with resolutions of 256x256 and 512x512.