DeepAI AI Chat
Log In Sign Up

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise

by   Arpit Bansal, et al.

Standard diffusion models involve an image transform – adding Gaussian noise – and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongly dependent on the choice of image degradation, and in fact an entire family of generative models can be constructed by varying this choice. Even when using completely deterministic degradations (e.g., blur, masking, and more), the training and test-time update rules that underlie diffusion models can be easily generalized to create generative models. The success of these fully deterministic models calls into question the community's understanding of diffusion models, which relies on noise in either gradient Langevin dynamics or variational inference, and paves the way for generalized diffusion models that invert arbitrary processes. Our code is available at


page 1

page 13

page 15

page 16

page 19

page 20

page 21

page 22


Subspace Diffusion Generative Models

Score-based models generate samples by mapping noise to data (and vice v...

Denoising Diffusion Gamma Models

Generative diffusion processes are an emerging and effective tool for im...

Analyzing Diffusion as Serial Reproduction

Diffusion models are a class of generative models that learn to synthesi...

Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers

We develop a framework for non-asymptotic analysis of deterministic samp...

Modelos Generativos basados en Mecanismos de Difusión

Diffusion-based generative models are a design framework that allows gen...

PFGM++: Unlocking the Potential of Physics-Inspired Generative Models

We introduce a new family of physics-inspired generative models termed P...

TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets

Diffusion models have achieved great success in a range of tasks, such a...

Code Repositories


🌞 Profile of 𝘼𝙡𝙚𝙭𝙖𝙣𝙙𝙚𝙧 𝙍𝙤𝙜𝙖𝙡𝙨𝙠𝙞𝙮

view repo