AI Paper Atlas

Research map / Image generation / Editing and style transfer

SliderSpace: Decomposing the Visual Capabilities of Diffusion Models

Rohit Gandikota, Zongze Wu, Richard Zhang, David Bau, Eli Shechtman, Nick Kolkin

ICCV 2025 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing · 21 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
apply SliderSpace sliders (3 random of 32) to the distilled modelSDXL-DMD · Concept decomposition (6 concepts)DreamSim inter-image diversityImproved
apply SliderSpace sliders to the distilled modelSDXL-DMD · Concept decomposition (6 concepts)CLIP scoreNo clear effect
use unsupervised SliderSpace instead of supervised Concept SlidersSDXL-DMD art styles · Art styles vs reference artist distributionFID: 32.86 -> 19.12Improved
use SliderSpace instead of LLM-generated style promptsSDXL-DMD art styles · Art styles vs reference artist distributionFID: 38.84 -> 19.12Improved
use SliderSpace instead of a generic art promptSDXL-DMD art styles · Art styles vs reference artist distributionFID: 76.08 -> 19.12Improved
use SliderSpace images instead of real artist-name promptsSDXL-DMD art styles · Art styles user studywin rate (Diverse / Useful %): 54 diverse, 63 usefulMixed
add SliderSpace trained on COCO prompts to distilled modelSDXL-DMD · COCO-30kFID-30k: 15.52 -> 12.12Improved
add SliderSpace trained on COCO prompts to distilled modelSDXL-DMD · COCO-30kCLIP score: 28.92 -> 29.13Improved
use SliderSpace instead of Concept Sliders for same number of slidersSliderSpace training · Training timetraining speed: 8 times fasterImproved

Later papers that compared with this method

1 later accepted paper reports SliderSpace as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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