Guiding a Diffusion Model with a Bad Version of Itself

Studies control of image quality separately from diversity. Autoguidance steers diffusion sampling using a smaller or less-trained version of the same model rather than an unconditional model.

Studies control of image quality separately from diversity. Autoguidance steers diffusion sampling using a smaller or less-trained version of the same model rather than an unconditional model.

When reading the original paper, identify its problem, inputs, outputs, and methodological assumptions.

Studies control of image quality separately from diversity. Autoguidance steers diffusion sampling using a smaller or less-trained version of the same model rather than an unconditional model.

Check the baselines, datasets, evaluation protocol, and ablations in the original paper. This directory overview does not provide an independent evaluation or experimental results table.