Reusing Computation in Text-to-Image Diffusion for Efficient Image Generation arxiv.org 41 points by gidellav 6 days ago
operator-name 2 days ago This looks similar to https://github.com/chengzeyi/ParaAttention or https://github.com/ali-vilab/TeaCache.It’s a shame they don’t compare against or mention them.
transformi 2 days ago Interesting approach! Remind me the early insights that neurons in DNN that capture similar concepts.
This looks similar to https://github.com/chengzeyi/ParaAttention or https://github.com/ali-vilab/TeaCache.
It’s a shame they don’t compare against or mention them.
Interesting approach! Remind me the early insights that neurons in DNN that capture similar concepts.