←back to thread

Efficient high-resolution image synthesis with linear diffusion transformer

(nvlabs.github.io)
220 points Vt71fcAqt7 | 2 comments | 16 Oct 24 14:56 UTC | HN request time: 0.561s | source
1. smusamashah ◴[16 Oct 24 15:11 UTC] No.41860021[source]▶
> (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput. Moreover, Sana-0.6B can be deployed on a 16GB laptop GPU, taking less than 1 second to generate a 1024 × 1024 resolution image.
replies(1): >>41860691 #
2. ◴[16 Oct 24 16:01 UTC] No.41860691[source]▶