OpenCodePapers

text-to-image-generation-on-drawbench

Text-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.
PaperCodeAesthetics (Laion Aesthtetics Predictor)Human Preference Alignement (HPSv2)Text Alignement (SentenceBERT)ModelNameReleaseDate
Curriculum Direct Preference Optimization for Diffusion and Consistency Models✓ Link6.18290.28510.5812LCM (Curriculum DPO)2024-05-22
Diffusion Model Alignment Using Direct Preference Optimization✓ Link6.04300.28140.5720LCM (DPO)2023-11-21
Training Diffusion Models with Reinforcement Learning✓ Link6.01210.28030.5721LCM (DDPO)2023-05-22
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference✓ Link5.80380.26100.5602LCM2023-10-06
Curriculum Direct Preference Optimization for Diffusion and Consistency Models✓ Link5.70600.26810.6234Stable Diffusion 1.5 (Curriculum DPO)2024-05-22
Training Diffusion Models with Reinforcement Learning✓ Link5.67480.26730.6024Stable Diffusion 1.5 (DDPO)2023-05-22
Diffusion Model Alignment Using Direct Preference Optimization✓ Link5.62050.26720.6075Stable Diffusion 1.5 (DPO)2023-11-21
High-Resolution Image Synthesis with Latent Diffusion Models✓ Link5.42920.26460.5997Stable Diffusion 1.52021-12-20
Check out how to contribute new results.