A free Chinese image model passed a million downloads in a week.
Chinese lab OpenMOSS released MOSS-Image on 16 October, a free model that writes legible text inside pictures. Hugging Face counts over 1.4 million downloads of its version for ComfyUI, a popular image-making app. Users have already built faster and smaller versions, and the weights carry a permissive Apache 2.0 licence.
Why it mattersYou can download it and make images on your own computer at no cost. Posters, menus and slides with readable text no longer need a paid tool.
Read in the app — free, in 9 languages
Related stories
Canva trained its first image model on templates, not photos.2026-10-23Hugging Face built a chatbot that reads DNA and explains mutations.
2026-10-22A startup says AI did most of the work on its new coding model.
2026-10-22Mistral's new voice models listen for when you stop talking.
2026-10-21A new AI model writes its answers all at once, not word by word.
2026-10-20