TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Medical/Image Generation/DrawBench

Image Generation on DrawBench

Metric: Human Preference Alignement (HPSv2) (lower is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Human Preference Alignement (HPSv2)▲Extra DataPaperDate↕Code
1LCM0.261NoLatent Consistency Models: Synthesizing High-Res...2023-10-06Code
2Stable Diffusion 1.50.2646NoHigh-Resolution Image Synthesis with Latent Diff...2021-12-20Code
3Stable Diffusion 1.5 (DPO)0.2672NoDiffusion Model Alignment Using Direct Preferenc...2023-11-21Code
4Stable Diffusion 1.5 (DDPO)0.2673NoTraining Diffusion Models with Reinforcement Lea...2023-05-22Code
5Stable Diffusion 1.5 (Curriculum DPO)0.2681NoCurriculum Direct Preference Optimization for Di...2024-05-22Code
6LCM (DDPO)0.2803NoTraining Diffusion Models with Reinforcement Lea...2023-05-22Code
7LCM (DPO)0.2814NoDiffusion Model Alignment Using Direct Preferenc...2023-11-21Code
8LCM (Curriculum DPO)0.2851NoCurriculum Direct Preference Optimization for Di...2024-05-22Code