Translated data: The aMUSEd model introduced by Hugging Face can generate images in just a few seconds, utilizing a lightweight text-to-image model that employs the Masked Image Model (MIM) architecture. This approach significantly reduces the number of inference steps, enhancing both the generation speed and interpretability. The aMUSEd model is available for trial on Hugging Face's demo and is currently provided as a research preview, licensed under the OpenRAIL license. It encourages the community to further explore non-diffusion frameworks for image generation.