AI Paper Atlas

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

Say Cheese! Detail-Preserving Portrait Collection Generation via Natural Language Edits

Zelong Sun, Jiahui Wu, Ying Ba, Dong Jing, Zhiwu Lu

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 0 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 supervised fine-tuning on CHEESE (ablation)IP-Adapter (zero-shot) · CHEESE test setQwen-PF: 0.428 -> 0.683Improved
add supervised fine-tuning on CHEESE (ablation)IP-Adapter (zero-shot) · CHEESE test setCLIP-T: 0.406 -> 0.421Improved
add supervised fine-tuning on CHEESE (ablation)IP-Adapter (zero-shot) · CHEESE test setDINO-I: 0.824 -> 0.728Hurt
add ConsistencyNet (ablation)+ SFT · CHEESE test setQwen-DP: 0.783 -> 0.832Improved
add ConsistencyNet (ablation)+ SFT · CHEESE test setQwen-PF: 0.683 -> 0.673Hurt
add Fusion IP-Adapter (ablation)+ ConNet · CHEESE test setQwen-PF: 0.673 -> 0.723Improved
add alignment loss (ablation)+ Fusion IP-A · CHEESE test setQwen-PF: 0.723 -> 0.777Improved
add alignment loss (ablation)+ Fusion IP-A · CHEESE test setDINO-I: 0.732 -> 0.753Improved
add teacher forcing (ablation)+ Align Loss · CHEESE test setQwen-DP: 0.836 -> 0.855Improved
add teacher forcing (ablation)+ Align Loss · CHEESE test setQwen-PF: 0.777 -> 0.793Improved
add teacher forcing (ablation)+ Align Loss · CHEESE test setCLIP-T: 0.426 -> 0.436Improved
validate annotations with CLIP ViT-G/14 instead of ViT-B/32 in inversion-based validation (ablation)CHEESE annotation pipeline · modification text quality (qualitative)text qualityImproved

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