AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

OminiControl: Minimal and Universal Control for Diffusion Transformer

Zhenxiong Tan, Songhua Liu, Xingyi Yang, Qiaochu Xue, Xinchao Wang

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 246 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
condition on all transformer blocks instead of early blocks only (ablation)OminiControl · Canny-to-imageF1 score: 0.23 -> 0.38Improved
condition on all transformer blocks instead of early blocks only (ablation)OminiControl · Canny-to-imageFID: 25.66 -> 20.63Improved
increase LoRA rank from 4 to 16 (ablation)OminiControl · Canny-to-imageF1 score: 0.380 -> 0.407Improved
increase LoRA rank from 4 to 16 (ablation)OminiControl · Canny-to-imageFID: 20.63 -> 19.71Improved
use LoRA rank 1 instead of 4 (ablation)OminiControl · Canny-to-imageCLIP score: 0.761 -> 0.765No clear effect
use unified sequence concatenation instead of direct feature adding (ablation)OminiControl · Canny-to-image training losstraining lossImproved
shift condition position indices instead of sharing positions (ablation)OminiControl · subject-driven generationtraining convergence and qualityImproved
train on Subjects200K instead of data augmentation (ablation)OminiControl · subject-driven generationqualitative novelty of viewsImproved
keep LoRA on normalization layers and W_Q, W_K projections (ablation)OminiControl · conditional renderingqualitative control qualityImproved
keep LoRA on value projections W_V (ablation)OminiControl · conditional renderingqualitative control qualityNo clear effect
use OminiControl instead of ControlNet Pro on deblurringOminiControl · DeblurMSE: 338 -> 62Improved
use OminiControl instead of ControlNet Pro on colorizationOminiControl · ColorizationMSE: 994 -> 73Improved

Later papers that compared with this method

15 later accepted papers report OminiControl as a baseline in their results tables; 13 of them report a better number on most of the results they share with it.

7 more not listed.

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