Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI
Catalog snapshot
Repository health snapshot: 75 forks and 10 open issues at review time. Platform support is inferred conservatively from repository topics.
Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI Fossfits includes transfusion-pytorch as an actively maintained image ai option: its public repository was updated on 2026-09-04, uses the MIT license, and had 1,402 stars when reviewed. Check its documentation and release notes before production adoption.
artificial intelligence · attention · deep learning · flow matching · multi modal