Mohammad Norouzi, David Chan, Jonathan Ho, William Chan, Jonathan ©2021, Chitwan Ho, William Saharia, Mohammad Fleet, Tim Norouzi, Salimans
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation benchmark, without any assistance from auxiliary image classifiers to boost sample quality. A cascaded diffusion model comprises a pipeline of multiple diffusion models that generate images of increasing resolution, beginning with a standard diffusion model at the lowest resolution, followed by one or more super-resolution diffusion models that successively upsample the image and add higher resolution details. We find that the sample quality of a cascading pipeline relies crucially on conditioning augmentation, our proposed method of data augmentation of the lower resolution conditioning inputs to the super-resolution models. Our experiments show that conditioning augmentation prevents compounding error during sampling in a cascaded model, helping us to train cascading pipelines achieving FID scores of 1.48 at 64×64, 3.52 at 128×128 and 4.88 at 256×256 resolutions, outperforming BigGAN-deep, and classification accuracy scores of 63.02% (top-1) and 84.06% (top-5) at 256×256, outperforming VQ-VAE-2.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.15282")
get_code_for_paper("2106.15282")
have("2106.15282")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2106.15282.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2106.15282)
Connect an agent — have() is free.