1.58-bit FLUX
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
presents the first successful approach to quantizing the state-of-the-art text-to-image generation model, FLUX.1-dev, using 1.58-bit weights (i.e., values in {-1, 0, +1}); the method relies on self-supervision from the FLUX.1-dev model and maintains comparable performance for generating 1024 x 1024 images as the original FLUX model.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack