FLUX is fast and it's open source

FLUX is now much faster on Replicate, and all optimizations have been made open-source for the community. Key improvements include model optimization using torch.compile and fast CuDNN attention kernels, along with a new synchronous HTTP API. The open-source initiative aims to make these enhancements accessible for further advancements. Users can fine-tune, edit, and deploy custom versions of FLUX, and explore model outputs on a new playground.