Abstract

We present 1.58-bit FLUX, 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}) while maintaining comparable performance for generating 1024 x 1024 images. Notably, our quantization method operates without access to image data, relying solely on self-supervision from the FLUX.1-dev model. Additionally, we develop a custom kernel optimized for 1.58-bit operations, achieving a 7.7x reduction in model storage, a 5.1x reduction in inference memory, and improved inference latency. Extensive evaluations on the GenEval and T2I Compbench benchmarks demonstrate the effectiveness of 1.58-bit FLUX in maintaining generation quality while significantly enhancing computational efficiency.

Paper: https://arxiv.org/abs/2412.18653

Code: https://github.com/Chenglin-Yang/1.58bit.flux (coming soon)

  • db0M
    link
    fedilink
    English
    1221 days ago

    None of them are truly open source, but many are free to use without many restrictions . Flux dev unfortunately isn’t one of them, not even allowing open source services like the horde to use it

    • Rikudou_Sage
      link
      fedilink
      English
      221 days ago

      Hmm, just reading the license, which part forbids the use by free services like the Horde? It seems like it should be allowed.

      • db0M
        link
        fedilink
        English
        321 days ago

        It’s written in a way which forbids people serving it as a service.

        • Rikudou_Sage
          link
          fedilink
          English
          021 days ago

          Well, that’s what I’m saying, it didn’t feel like it to me.

          • db0M
            link
            fedilink
            English
            121 days ago

            We’ve gone through it with a fine tooth comb. There’s statements in there that don’t give any exceptions for free services