AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Models

Yusuf Dalva, Hidir Yesiltepe, Pinar Yanardag

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 7 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 L_latent to semantic loss (ablation)ViDiT · Ablation (face directions)DINO: 0.832 -> 0.891Improved
add L_latent to semantic loss (ablation)ViDiT · Ablation (face directions)LPIPS: 0.121 -> 0.093Improved
add L_latent to semantic loss (ablation)ViDiT · Ablation (face directions)CLIP-T: 0.409 -> 0.406No clear effect
increase training pairs from 10 to 1000 (ablation)ViDiT · Ablation (face directions)DINO: 0.869 -> 0.891Improved
increase training pairs from 100 to 1000 (ablation)ViDiT · Ablation (face directions)LPIPS: 0.136 -> 0.093Improved
increase training pairs from 10 to 100 (ablation)ViDiT · Ablation (face directions)CLIP-T: 0.403 -> 0.425Improved
increase training pairs from 10 to 100 (ablation)ViDiT · Ablation (face directions)LPIPS: 0.098 -> 0.136Hurt
use DDPM inversion instead of DDIM inversion (ablation)ViDiT real image editing · real imagesidentity preservation (qualitative)Improved
apply edit at 0.4T instead of full T (ablation)ViDiT · generated facesedit strength vs identity (qualitative)Mixed
replace text prompt with learned visual direction vs InstructPix2PixViDiT · Text-driven editing comparison (200 pairs, Asian and Smile)LPIPS: 0.059 -> 0.030Improved
use ViDiT instead of Prompt2PromptViDiT · Text-driven editing comparison (200 pairs, Asian and Smile)DINO: 0.867 -> 0.929Improved
use ViDiT instead of Concept SlidersViDiT · Text-driven editing comparison (200 pairs, Asian and Smile)CLIP-T: 0.325 -> 0.407Improved

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