Research map / Image generation / Text-to-image diffusion
DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models
Revant Teotia, Candace Ross, Karen Ullrich, Sumit Chopra, Adriana Romero-Soriano, Melissa Hall, Matthew Muckley
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 |
|---|---|---|---|
| increase model size from LDM2.1 (1.5B) to FLUX.1-dev (12B) | text-to-image models · COCO-DIMCIM | Does-It Metric: 0.815 -> 0.785 | Hurt |
| increase model size from LDM2.1 (1.5B) to LDM3.5L (8.1B) | text-to-image models · COCO-DIMCIM | Can-It Metric: 0.299 -> 0.374 | Improved |
| increase CFG scale from 2.0 to 7.5 (ablation) | Flow-Int · COCO-DIMCIM | Can-It Metric: 0.261 -> 0.315 | Improved |
| increase CFG scale from 2.0 to 7.5 (ablation) | Flow-Int · COCO-DIMCIM | Does-It Metric: 0.839 -> 0.802 | Hurt |
| use FLUX.1-dev (12B) instead of LDM3.5L (8.1B) | text-to-image models · COCO-DIMCIM | Can-It Metric: 0.374 -> 0.326 | Hurt |
| match training-image attribute skew to generated attribute skew | Flow-Int (CC12M) · COCO-DIMCIM concept-attribute pairs | Does-It Metric correlation: 0.85 | Improved |
Closest papers by meaning
- Elucidating the design space of language models for image generation (ICML 2025 · similarity 0.85)
- Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation (ICLR 2024 · similarity 0.85)
- SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation (CVPR 2025 · similarity 0.85)
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.85)
- TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models (ICLR 2025 · similarity 0.85)
- Image Generation Diversity Issues and How to Tame Them (CVPR 2025 · similarity 0.85)
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.
