AI Paper Atlas

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

One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations

Yiming Zhu, Hongyu Liu, Yibing Song, Ziyang Yuan, Xintong Han, Chun Yuan, Qifeng Chen, Jue Wang

NeurIPS 2022 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 17 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 scale parameter in semantic alignment (ablation)FFCLIP · CelebA-HQ Aged 10age distance: 13.9412 -> 9.8874Improved
add translation parameter in semantic alignment (ablation)FFCLIP · CelebA-HQ Aged 10age distance: 20.0762 -> 9.8874Improved
add scale parameter (ablation)FFCLIP · CelebA-HQ Baldhair pixel count: 0.0630 -> 0.0279Improved
add scale parameter (ablation)FFCLIP · CelebA-HQ Red hairhair color difference: 0.7082 -> 0.7171Hurt
use 4 modulation blocks instead of 0 (ablation)FFCLIP · CelebA-HQ Baldhair pixel count: 0.2689 -> 0.0279Improved
increase modulation blocks from 4 to 6 (ablation)FFCLIP · CelebA-HQediting metrics: Bald 0.0279 -> 0.0236; Angry 0.5810 -> 0.7380Mixed
increase modulation blocks from 4 to 10 (ablation)FFCLIP · CelebA-HQ Baldhair pixel count: 0.0279 -> 0.1720Hurt
use 4 blocks instead of 2 (ablation)FFCLIP · CelebA-HQ Aged 10age distance: 18.5182 -> 9.8874Improved
use FFCLIP instead of StyleCLIPFFCLIP vs StyleCLIP · CelebA-HQ Aged 10age distance: 17.0053 -> 9.8874Improved
use FFCLIP instead of StyleCLIP in human votingFFCLIP vs StyleCLIP · CelebA-HQ Baldhuman vote share (%): 8.6 -> 85.7Improved

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