Tootfinder

Ambient Diffusion Omni: Training Good Models with Bad Data
Giannis Daras, Adrian Rodriguez-Munoz, Adam Klivans, Antonio Torralba, Constantinos Daskalakis
https://arxiv.org/abs/2506.10038

Ambient Diffusion Omni: Training Good Models with Bad Data
We show how to use low-quality, synthetic, and out-of-distribution images to improve the quality of a diffusion model. Typically, diffusion models are trained on curated datasets that emerge from highly filtered data pools from the Web and other sources. We show that there is immense value in the lower-quality images that are often discarded. We present Ambient Diffusion Omni, a simple, principled framework to train diffusion models that can extract signal from all available images during train…

style is often more substance than most ppl give it credit for. emotion, chemistry, dark ambient swag.