Moss Image

Moss Image puts MOSS-Image, the open text-to-image model from the OpenMOSS team, in a browser tab so you can test prompts without a GPU, Docker image or local install. It makes images from a plain-English prompt, renders readable English and Chinese lettering inside the image, supports JSON layout prompts and an HD or 2K canvas, and gives you seed, steps, guidance and negative prompt controls. Sign-up includes free credits, with paid plans for more. This is an independent site, not affiliated with OpenMOSS.