Text-to-Image Generation on UniGenBench++ in-domain
73.95Semantic ConsistencyFLUX.1-dev + UnifiedReward-Flex
Evaluation results
| Method | Links | |
|---|---|---|
| FLUX.1-dev + UnifiedReward-FlexBackbone=FLUX.1-dev, Optimization=GRPO, Reward Model=UnifiedReward-Flex, Sampling steps=30, CFG scale=3.52026.02 | 73.95 | |
| FLUX.1-dev + UnifiedReward-ThinkBackbone=FLUX.1-dev, Optimization=GRPO, Reward Model=UnifiedReward-Think, Sampling steps=30, CFG scale=3.52026.02 | 68.89 | |
| FLUX.1-dev + UnifiedRewardBackbone=FLUX.1-dev, Optimization=GRPO, Reward Model=UnifiedReward, Sampling steps=30, CFG scale=3.52026.02 | 60.87 | |
| FLUX.1-devSampling steps=30, CFG scale=3.52026.02 | 59.39 | |
| FLUX.1-dev + PickScoreBackbone=FLUX.1-dev, Optimization=GRPO, Reward Model=PickScore, Sampling steps=30, CFG scale=3.52026.02 | 58.63 | |
| FLUX.1-dev + HPSv3Backbone=FLUX.1-dev, Optimization=GRPO, Reward Model=HPSv3, Sampling steps=30, CFG scale=3.52026.02 | 57.98 | |
| FLUX.1-dev + HPSv2Backbone=FLUX.1-dev, Optimization=GRPO, Reward Model=HPSv2, Sampling steps=30, CFG scale=3.52026.02 | 57.77 |