AI Paper Atlas

Research map / Image generation / Editing and style transfer

AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfer

Yongwen Lai, Chaoqun Wang

ECCV 2026 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the single style LoRA (ablation)AnyStyle · Style transfer (40 images)CLIP-Style: 57.3314 -> 68.2336Improved
add the single style LoRA (ablation)AnyStyle · Style transfer (40 images)CLIP-T: 29.9431 -> 32.0717Improved
add the single style LoRA (ablation)AnyStyle · Style transfer (40 images)DINO-Style: 0.6170 -> 0.7234Improved
modulate query only instead of key only (ablation)AnyStyle · Style transfer (40 images)DS-Content: 0.5198 -> 0.4210Improved
modulate query only instead of key only (ablation)AnyStyle · Style transfer (40 images)DINO-Style: 0.7225 -> 0.7147Hurt
modulate query only instead of query+key (ablation)AnyStyle · Style transfer (40 images)CLIP-Style: 67.1565 -> 67.9291Improved
use single style LoRA instead of dual-LoRAAnyStyle · Style transfer (40 images)CLIP-Style: 63.3469 -> 67.9291Improved
use our style LoRA instead of B-LoRA'sAnyStyle · Style transfer (40 images)DINO-Style: 0.7070 -> 0.7234Improved
use our style LoRA instead of UnZipLoRA'sAnyStyle · Style transfer (40 images)DINO-Style: 0.7153 -> 0.7234Improved
use attention-based content injection instead of LoRA-basedcontent reconstruction · ReconstructionPSNR: 11.7899 -> 18.0029Improved
swap FLUX backbone for SDXLAnyStyle · Style transfer (40 images)CLIP-Style: 67.9291 -> 66.4223Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy