Pith. sign in

REVIEW 2 cited by

Customizing Text-to-Image Models with a Single Image Pair

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 2405.01536 v2 pith:KPNMHXT6 submitted 2024-05-02 cs.CV cs.GRcs.LG

Customizing Text-to-Image Models with a Single Image Pair

classification cs.CV cs.GRcs.LG
keywords styleimagecontentpairstylisticmethodsingledifference
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Art reinterpretation is the practice of creating a variation of a reference work, making a paired artwork that exhibits a distinct artistic style. We ask if such an image pair can be used to customize a generative model to capture the demonstrated stylistic difference. We propose Pair Customization, a new customization method that learns stylistic difference from a single image pair and then applies the acquired style to the generation process. Unlike existing methods that learn to mimic a single concept from a collection of images, our method captures the stylistic difference between paired images. This allows us to apply a stylistic change without overfitting to the specific image content in the examples. To address this new task, we employ a joint optimization method that explicitly separates the style and content into distinct LoRA weight spaces. We optimize these style and content weights to reproduce the style and content images while encouraging their orthogonality. During inference, we modify the diffusion process via a new style guidance based on our learned weights. Both qualitative and quantitative experiments show that our method can effectively learn style while avoiding overfitting to image content, highlighting the potential of modeling such stylistic differences from a single image pair.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

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

  1. PoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation

    cs.GR 2026-07 conditional novelty 6.0

    Two-stage text-guided mesh deformation (Laplacian CLIP scaling + attention-shared SDS Jacobian sculpting) better preserves source pose while aligning to text than TextDeformer or MeshUp.

  2. PoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation

    cs.GR 2026-07 conditional novelty 5.0

    PoseAlign splits text-guided mesh deformation into Laplacian-based global pose scaling and attention-sharing SDS local sculpting to keep pose while matching text.