Hugging Face Blog·· 2024-01-04AI score34
Hugging Face Releases aMUSEd: An Efficient Non-Diffusion Text-to-Image Model
Welcome aMUSEd: Efficient Text-to-Image Generation
AI briefing
Hugging Face releases aMUSEd, a non-diffusion text-to-image model with approximately 800M parameters. It is an open-source reproduction of Google's MUSE, using masked image modeling (MIM) with fewer inference steps and greater interpretability.
Open original huggingface.co