Research map / Image generation / Text-to-image diffusion
Trade-offs in Image Generation: How Do Different Dimensions Interact?
Sicheng Zhang, Binzhu Xie, Zhonghao Yan, Yuli Zhang, Donghao Zhou, Xiaofei Chen, Shi Qiu, Jiaqi Liu, Guoyang Xie, Zhichao Lu
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 |
|---|---|---|---|
| fine-tune with DTM | Sana · TRIG-Bench T2I | TRIGScore Bias: 0.48 -> 0.66 | Improved |
| fine-tune with DTM | Sana · TRIG-Bench T2I | TRIGScore Ambiguity: 0.58 -> 0.62 | Improved |
| fine-tune with DTM | Sana · TRIG-Bench T2I | TRIGScore Relation: 0.63 -> 0.67 | Improved |
| fine-tune with DTM | Sana · TRIG-Bench T2I | TRIGScore Realism: 0.57 -> 0.60 | Improved |
| add DTM-guided training | HQEdit · TRIG-Bench image-editing | TRIGScore Ambiguity: 0.66 -> 0.71 | Improved |
| add DTM-guided training | HQEdit · TRIG-Bench image-editing | TRIGScore Content: 0.64 -> 0.64 | No clear effect |
| add DTM-guided training | FLUX-IP-Adapter · TRIG-Bench subject-driven | TRIGScore Ambiguity: 0.55 -> 0.66 | Improved |
| add DTM-guided training | FLUX-IP-Adapter · TRIG-Bench subject-driven | TRIGScore Style: 0.66 -> 0.66 | No clear effect |
| fine-tune with DTM | Sana · TRIG-Bench T2I | TRIGScore Knowledge: 0.49 -> 0.50 | No clear effect |
| add DTM fine-tuning (ablation) | SD v3.5 · HEIM | Toxicity: 0.38 -> 0.55 | Improved |
| add DTM fine-tuning (ablation) | SD v3.5 · HEIM | Bias: 0.50 -> 0.60 | Improved |
| add DTM fine-tuning (ablation) | SD v3.5 · HEIM | Knowledge: 0.25 -> 0.33 | Improved |
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.
- HQEdit — HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing (ICLR 2025) · better on 1 of 1 shared result
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
- OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation (NeurIPS 2025 · similarity 0.89)
- Learning Visual Generative Priors without Text (CVPR 2025 · similarity 0.86)
- When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization (NeurIPS 2025 · similarity 0.86)
- Improving Long-Text Alignment for Text-to-Image Diffusion Models (ICLR 2025 · similarity 0.86)
- ImagenHub: Standardizing the evaluation of conditional image generation models (ICLR 2024 · similarity 0.86)
- Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models (AAAI 2025 · similarity 0.86)
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.
