AI Paper Atlas

Research map / Image generation / Editing and style transfer

Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing

Rishubh Parihar, Or Patashnik, Daniil Ostashev, Venkatesh Babu Radhakrishnan, Daniel Cohen-Or, Kuan-Chieh Jackson Wang

CVPR 2026 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing

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
inject strength in modulation space instead of as an extra text token (ablation)Kontinuous Kontext · PIEBenchdelta_smooth: 1.468 -> 0.329Improved
add pooled CLIP text embedding as input to the strength projector (ablation)Kontinuous Kontext · PIEBenchdelta_smooth: 1.092 -> 0.329Improved
add pooled CLIP text embedding as input to the strength projector (ablation)Kontinuous Kontext · PIEBenchCLIP-dir: 0.141 -> 0.241Improved
filter synthetic training data by smoothness and inversion quality (ablation)Kontinuous Kontext · PIEBenchdelta_smooth: 0.483 -> 0.329Improved
filter synthetic training data by smoothness and inversion quality (ablation)Kontinuous Kontext · PIEBenchCLIP-dir: 0.228 -> 0.241Improved
use learned strength projector instead of CFG scale at inferenceFlux Kontext · PIEBenchdelta_smooth: 152.205 -> 0.329Improved
use learned strength projector instead of cross-attention reweighting at inferenceFlux Kontext · PIEBenchdelta_smooth: 120.760 -> 0.329Improved
use Kontinuous Kontext instead of video inbetweening (WAN) for intermediate editsKontinuous Kontext · PIEBenchdelta_smooth / CLIP-dir: delta_smooth 0.853 -> 0.329; CLIP-dir 0.269 -> 0.241Mixed
use Kontinuous Kontext instead of MARBLE for material strengthKontinuous Kontext · material editing, PIEBench subsetdelta_smooth / CLIP-dir: delta_smooth 2.577 -> 0.350; CLIP-dir 0.157 -> 0.101Mixed
use Kontinuous Kontext instead of ConceptSlidersKontinuous Kontext · 11 sliders, 44 generated imagesCLIP-dir: 0.186 -> 0.382Improved
extrapolate edit strength beyond s=1Kontinuous Kontext · qualitative failure caseedit extentHurt
scale text-token modulation parameters directly at inference by a scalar (ablation)Flux Kontext · qualitativeedit strength controlNo clear effect

Later papers that compared with this method

1 later accepted paper reports Kontinuous Kontext as a baseline in their results tables; 0 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 2 of 3 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