OpenCodePapers

text-to-image-generation-on-t2i-compbench

Image GenerationText-to-Image Generation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeColorTextureSpatialShapeComplexNon-SpatialModelNameReleaseDate
MANGO: Unleashing Image Generation Capability of Unified Multimodal Models0.86630.78750.40450.61920.45290.3741MANGO-4B2026-09-08
SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation✓ Link0.86330.78570.50430.62730.4473SCOPE (Qwen-Image)2026-10-15
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation0.85420.7550.47340.62960.41360.3199IV-CoT (OpenUni-L-1024)2026-06-23
ELDiff: When Evidential Learning Meets Text-to-Image Diffusion✓ Link0.84520.74350.39250.62410.464ELDiff (SD v3.5 Medium)2026-06-18
PromptEnhancer: Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward0.84420.72960.44720.62120.3864PromptEnhancer (+PE) with Qwen-Image2026-06-03
ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation✓ Link0.8380.7390.388ISAC (SD3.5-M)2025-05-27
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization✓ Link0.79350.71360.23410.60470.3229SDXL-BiDPO2026-05-27
SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model✓ Link0.78540.6810.5467Switti + SynVAR2026-08-08
Discriminative Probing and Tuning for Text-to-Image Generation0.51510.49380.15450.39610.30290.3084DPT + SC2024-03-07
CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance✓ Link0.4085Qwen-Image with SMC-CFG2026-03-03
PromptEnhancer: Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward0.7434PromptEnhancer (+PE) with HY-Image 2.12026-06-03
SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model✓ Link0.460.3902Infinity + SynVAR2026-08-08
Check out how to contribute new results. Then edit this file on GitLab or GitHub.