Pith. sign in

REVIEW 1 cited by

Real-World Image Variation by Aligning Diffusion Inversion Chain

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.18729 v3 pith:A5RCWCYT submitted 2023-05-30 cs.CV

classification cs.CV
keywords imagediffusionvariationsgenerationimagesreal-worldalignmentdistribution
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent diffusion model advancements have enabled high-fidelity images to be generated using text prompts. However, a domain gap exists between generated images and real-world images, which poses a challenge in generating high-quality variations of real-world images. Our investigation uncovers that this domain gap originates from a latents' distribution gap in different diffusion processes. To address this issue, we propose a novel inference pipeline called Real-world Image Variation by ALignment (RIVAL) that utilizes diffusion models to generate image variations from a single image exemplar. Our pipeline enhances the generation quality of image variations by aligning the image generation process to the source image's inversion chain. Specifically, we demonstrate that step-wise latent distribution alignment is essential for generating high-quality variations. To attain this, we design a cross-image self-attention injection for feature interaction and a step-wise distribution normalization to align the latent features. Incorporating these alignment processes into a diffusion model allows RIVAL to generate high-quality image variations without further parameter optimization. Our experimental results demonstrate that our proposed approach outperforms existing methods concerning semantic similarity and perceptual quality. This generalized inference pipeline can be easily applied to other diffusion-based generation tasks, such as image-conditioned text-to-image generation and stylization.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. VideoCrafter1: Open Diffusion Models for High-Quality Video Generation

    cs.CV 2023-10 unverdicted novelty 6.0 of 10

    Open-source text-to-video and image-to-video diffusion models generate high-quality 1024x576 videos, with the I2V variant claimed as the first to strictly preserve reference image content.

Pith tools