AI Paper Atlas

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

Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

Shihao Zhao, Dongdong Chen, Yen-Chun Chen, Jianmin Bao, Shaozhe Hao, Lu Yuan, Kwan-Yee K. Wong

NeurIPS 2023 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 65 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
Use shared multi-scale local condition injection rather than resized direct SPADE injection (ablation)Uni-ControlNet · Canny conditionFID: 25.89 -> 18.24Improved
Use multi-scale local condition injection rather than input-layer-only injection (ablation)Uni-ControlNet · Canny conditionFID: 22.22 -> 18.24Improved
Inject global condition into the main diffusion model as well as the control adapter (ablation)Uni-ControlNet · Content conditionFID: 27.06 -> 24.86Improved
Fine-tune local and global adapters separately instead of jointly from scratch (ablation)Uni-ControlNet · Canny conditionFID: 21.21 -> 18.24Improved
Further jointly fine-tune after separate adapter training (ablation)Uni-ControlNet · Canny conditionFID: 18.24 -> 18.80No clear effect
Use Uni-ControlNet rather than ControlNet for single-condition generationStable Diffusion controllable generation · COCO2017 val, HEDFID: 26.59 -> 17.86Improved
Use Uni-ControlNet rather than the strongest reported baselineStable Diffusion controllable generation · COCO2017 val, SketchFID: 18.83 -> 20.11Hurt
Use Uni-ControlNet rather than the strongest reported baselineStable Diffusion controllable generation · COCO2017 val, PosemAP: 0.5283 -> 0.2164Hurt
Use Uni-ControlNet rather than the strongest reported baselineStable Diffusion controllable generation · COCO2017 val, DepthMSE: 87.57 -> 91.05Hurt
Use Uni-ControlNet rather than the strongest reported baselineStable Diffusion controllable generation · COCO2017 val, SegmentationmIoU: 0.4431 -> 0.3160Hurt
Use Uni-ControlNet rather than ControlNetStable Diffusion controllable generation · COCO2017 val, MLSDSSIM: 0.7455 -> 0.6773Hurt
Use Uni-ControlNet rather than ControlNetStable Diffusion controllable generation · COCO2017 val, CannySSIM: 0.4828 -> 0.4911Improved

Later papers that compared with this method

15 later accepted papers report Uni-ControlNet as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.

7 more not listed.

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