Research map / Image generation / Text-to-image diffusion
Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
Shaojin Wu, Mengqi Huang, Wenxu Wu, Yufeng Cheng, Fei Ding, Qian He
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use generated second reference image instead of cropped parts of target (ablation) | UNO · Multi-subject driven generation benchmark | DINO: 0.529 -> 0.542 | Improved |
| use generated second reference image instead of cropped parts of target (ablation) | UNO · Multi-subject driven generation benchmark | CLIP-T: 0.308 -> 0.322 | Hurt |
| add progressive cross-modal alignment (ablation) | UNO · Multi-subject driven generation benchmark | DINO: 0.511 -> 0.542 | Improved |
| add progressive cross-modal alignment (ablation) | UNO · Multi-subject driven generation benchmark | CLIP-T: 0.322 -> 0.322 | No clear effect |
| add progressive cross-modal alignment (vs single-subject pair data only) (ablation) | UNO · DreamBench (single-subject) | DINO: 0.730 -> 0.760 | Improved |
| add progressive cross-modal alignment (vs single-subject pair data only) (ablation) | UNO · DreamBench (single-subject) | CLIP-T: 0.309 -> 0.304 | Hurt |
| add UnoPE instead of cloning target position index (ablation) | UNO · Multi-subject driven generation benchmark | DINO: 0.386 -> 0.542 | Improved |
| add UnoPE instead of cloning target position index (ablation) | UNO · Multi-subject driven generation benchmark | CLIP-T: 0.323 -> 0.322 | Hurt |
| add UnoPE position offset instead of no offset (ablation) | UNO · DreamBench (single-subject) | DINO: 0.470 -> 0.730 | Improved |
| use UnoPE instead of width-only offset (ablation) | UNO · DreamBench (single-subject) | DINO: 0.717 -> 0.730 | Improved |
| use UnoPE instead of height-only offset (ablation) | UNO · DreamBench (single-subject) | DINO: 0.678 -> 0.730 | Improved |
| use UnoPE instead of width-only offset (ablation) | UNO · Multi-subject driven generation benchmark | DINO: 0.508 -> 0.542 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- OmniGen — OmniGen: Unified Image Generation (CVPR 2025) · better on 4 of 6 shared results
- MS-Diffusion — MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance (ICLR 2025) · better on 3 of 3 shared results
- OminiControl — OminiControl: Minimal and Universal Control for Diffusion Transformer (ICCV 2025) · better on 2 of 3 shared results
- RealCustom++ — RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization (CVPR 2024) · better on 2 of 3 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
- SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation (CVPR 2024 · similarity 0.89)
- OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance (NeurIPS 2024 · similarity 0.88)
- Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator (CVPR 2025 · similarity 0.87)
- XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation (NeurIPS 2025 · similarity 0.87)
- MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance (ICLR 2025 · similarity 0.87)
- CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation (ICLR 2025 · similarity 0.87)
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.
