AI Paper Atlas

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

SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation

Paul Grimal, Michael Soumm, Hervé Le Borgne, Olivier Ferret, Akihiro Sugimoto

AAAI 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 1 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 SAGA (learned signal-aligned mean) at an intermediate timestepSD 1.4 · TIAM (4 entities)TIAM score: 1.0 -> 6.8Improved
use SAGA instead of InitNO (single intervention)SD 1.4 · TIAM (2 entities)TIAM score: 62.1 -> 74.7Improved
add GSN guidance after learning the distribution (SAGA+)SAGA on SD 1.4 · TIAM (2 entities)TIAM score: 74.7 -> 85.5Improved
use SAGA+ instead of SyngenSD 1.4 · TIAM (4 entities)TIAM score: 13.1 -> 17.9Improved
use SAGA+ instead of Attend&ExciteSD 1.4 · VQA Score (4 entities)VQA score: 49.8 -> 51.1Mixed
apply SAGA to SD 3SD 3 · TIAM (4 entities)TIAM score: 32.2 -> 63.2Improved
learn covariance as well as mean (SAGA-Sigma) (ablation)SAGA on SD 1.4 · TIAM (3 entities)TIAM score: 32.3 -> 37.1Improved
learn covariance as well as mean (SAGA-Sigma) (ablation)SAGA on SD 3 · TIAM (2 entities)TIAM score: 87.0 -> 86.6Hurt
use SAGA instead of BoxDiff for bounding-box conditioningSD 1.4 · TIAM (3 entities, bounding-box conditioned)TIAM score: 18.0 -> 34.4Improved
add GSN guidance to bounding-box SAGA (SAGA+) (ablation)SAGA on SD 1.4 with boxes · TIAM (3 entities, bounding-box conditioned)TIAM score: 34.4 -> 40.5Improved
vary the sampling step t at which SAGA is applied (ablation)SAGA on SD 1.4 · TIAM, Aesthetic, CLIP scoresnormalized average scoreMixed

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