Log In Sign Up

ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models

by   Jooyoung Choi, et al.

Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process in DDPM, it is challenging to generate images with the desired semantics. In this work, we propose Iterative Latent Variable Refinement (ILVR), a method to guide the generative process in DDPM to generate high-quality images based on a given reference image. Here, the refinement of the generative process in DDPM enables a single DDPM to sample images from various sets directed by the reference image. The proposed ILVR method generates high-quality images while controlling the generation. The controllability of our method allows adaptation of a single DDPM without any additional learning in various image generation tasks, such as generation from various downsampling factors, multi-domain image translation, paint-to-image, and editing with scribbles.


page 1

page 5

page 6

page 7

page 9

page 12

page 13

page 14


Denoising Diffusion Implicit Models

Denoising diffusion probabilistic models (DDPMs) have achieved high qual...

Lossy Image Compression with Conditional Diffusion Models

Denoising diffusion models have recently marked a milestone in high-qual...

Generative Probabilistic Image Colorization

We propose Generative Probabilistic Image Colorization, a diffusion-base...

f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation

Diffusion models (DMs) have recently emerged as SoTA tools for generativ...

Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

We present rectified flow, a surprisingly simple approach to learning (n...

Image Generation with Multimodal Priors using Denoising Diffusion Probabilistic Models

Image synthesis under multi-modal priors is a useful and challenging tas...

Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules

Work on fast weight programmers has demonstrated the effectiveness of ke...