AI Paper Atlas

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

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

Can Qin, Shu Zhang, Ning Yu, Yihao Feng, Xinyi Yang, Yingbo Zhou, Huan Wang, Juan Carlos Niebles, Caiming Xiong, Silvio Savarese, Stefano Ermon, Yun Fu and 1 more

NeurIPS 2023 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 24 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 MoE-style adapter (ablation)UniControl · six-task avgFID: 28.7 -> 25.7Improved
add task-aware HyperNet (on top of MoE adapter) (ablation)UniControl · six-task avgFID: 25.7 -> 24.0Improved
add TaskHyperNet (ablation)UniControl · Depth-to-imageFID: 23.7 -> 21.3Improved
unify nine tasks in one model instead of single-task ControlNetsUniControl · Depth-to-imageFID: 25.5 -> 21.3Improved
unify nine tasks in one model instead of single-task ControlNetsUniControl · HED-to-imageFID: 25.1 -> 23.6Improved
unify nine tasks in one model instead of single-task ControlNetsUniControl · Canny-to-imageFID: 22.7 -> 22.9No clear effect
unify nine tasks in one modelUniControl · Segmentation perceptual distanceimage perceptual distance: 0.693 -> 0.693No clear effect
unify nine tasks in one modelUniControl · Normal perceptual distanceimage perceptual distance: 0.778 -> 0.623Improved
unify nine tasks in one modelUniControl · Pose perceptual distanceimage perceptual distance: 0.747 -> 0.741Improved
unify nine tasks in one modelUniControl · model sizeparameters: 4.32B -> 1.44BImproved

Later papers that compared with this method

7 later accepted papers report UniControl as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

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