Excited to share Colored Noise Sampling (CNS)!π
Instead of injecting white noise, our SDE sampler exploits the inherent spectral bias of diffusion models. We dynamically color the injected noise to focus on frequencies where details are missing, substantially improving FID.π§΅1/9
1/6 Diffusion models are scaling up, but deploying a massive, monolithic network uniformly across the entire generative timeline is inherently inefficient.
Introducing Complexity-Balanced Splitting (CBS): a principled framework that allocates capacity exactly where needed!ππ§΅
Excited to share Colored Noise Sampling (CNS)!π
Instead of injecting white noise, our SDE sampler exploits the inherent spectral bias of diffusion models. We dynamically color the injected noise to focus on frequencies where details are missing, substantially improving FID.π§΅1/9
8/9 - Step-efficient inferenceβ‘
CNS at 100 steps already beats standard SDE at 1000 steps (FID 7.2 vs 7.8).
It is robust across solver orders (Euler, Heun, SRK2), and slots into FLUX.1-dev and FLUX.2-klein for text-to-image. All at inference time.