List your company
ResearchFormerly WizWand

Text-to-Image Generation on PickScore (Out-of-Domain)

0.291CLIP ScoreFlow-GRPO
0.227560.244030.26050.27697Jun 9, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Flow-GRPOBase Model=FLUX.1-dev, Strategy=single-reward RL fine-tuning2026.060.29121.850.311
Flow-DPPOBase Model=FLUX.1-dev, Strategy=single-reward RL fine-tuning2026.060.2921.60.3
Flow-DPPO + CPSBase Model=FLUX.1-dev, Strategy=single-reward RL fine-tuning2026.060.28921.910.305
Flow-CPSBase Model=FLUX.1-dev, Strategy=single-reward RL fine-tuning2026.060.28821.980.307
Flow-DPPO + CPSBase Model=FLUX2-klein-base-9B, Training Strategy=multi-reward RL fine-tuning2026.060.28722.970.37
Flow-DPPO + CPSBase Model=FLUX2-klein-base-9B, Strategy=multi-reward RL fine-tuning2026.060.28722.970.37
GRPO-GuardBase Model=FLUX.1-dev, Strategy=single-reward RL fine-tuning2026.060.28621.030.276
Flow-DPPOBase Model=FLUX2-klein-base-9B, Training Strategy=multi-reward RL fine-tuning2026.060.28222.90.368
Flow-DPPOBase Model=FLUX2-klein-base-9B, Strategy=multi-reward RL fine-tuning2026.060.28222.90.368
Flow-DPPO + CPSBase Model=SD3.5-medium, Training Strategy=multi-reward RL fine-tuning2026.060.27922.510.361
Flow-DPPO + CPSBase Model=SD3.5-medium, Strategy=multi-reward RL fine-tuning2026.060.27922.510.361
Flow-DPPOBase Model=FLUX2-klein-base-9B, Strategy=single-reward RL fine-tuning2026.060.27821.270.285
Flow-GRPOBase Model=FLUX2-klein-base-9B, Training Strategy=multi-reward RL fine-tuning2026.060.27722.620.357
Flow-GRPOBase Model=FLUX2-klein-base-9B, Strategy=multi-reward RL fine-tuning2026.060.27722.620.357
FLUX.1-devBase Model=FLUX.1-dev, Training Strategy=Pretrained baselines (before RL)2026.060.27621.910.304
Flow-CPSBase Model=FLUX2-klein-base-9B, Training Strategy=multi-reward RL fine-tuning2026.060.27622.850.364
FLUX.1-devBase Model=FLUX.1-dev, Strategy=Pretrained (before RL)2026.060.27621.910.304
Flow-CPSBase Model=FLUX2-klein-base-9B, Strategy=multi-reward RL fine-tuning2026.060.27622.850.364
Flow-CPSBase Model=FLUX2-klein-base-9B, Strategy=single-reward RL fine-tuning2026.060.27521.150.267
Diffusion-NFTBase Model=FLUX2-klein-base-9B, Training Strategy=multi-reward RL fine-tuning2026.060.27422.470.351
Diffusion-NFTBase Model=FLUX2-klein-base-9B, Strategy=multi-reward RL fine-tuning2026.060.27422.470.351
Flow-GRPOBase Model=SD3.5-medium, Training Strategy=multi-reward RL fine-tuning2026.060.27322.070.349
Flow-DPPOBase Model=SD3.5-medium, Training Strategy=multi-reward RL fine-tuning2026.060.27322.580.36
Flow-GRPOBase Model=SD3.5-medium, Strategy=multi-reward RL fine-tuning2026.060.27322.070.349
Flow-DPPOBase Model=SD3.5-medium, Strategy=multi-reward RL fine-tuning2026.060.27322.580.36
GRPO-GuardBase Model=SD3.5-medium, Training Strategy=multi-reward RL fine-tuning2026.060.27222.320.354
Flow-DPPO + CPSBase Model=SD3.5-medium, Strategy=single-reward RL fine-tuning2026.060.27220.50.246
GRPO-GuardBase Model=SD3.5-medium, Strategy=multi-reward RL fine-tuning2026.060.27222.320.354
Diffusion-NFTBase Model=SD3.5-medium, Training Strategy=multi-reward RL fine-tuning2026.060.26922.520.355
GRPO-GuardBase Model=FLUX2-klein-base-9B, Training Strategy=multi-reward RL fine-tuning2026.060.26921.990.349
Diffusion-NFTBase Model=SD3.5-medium, Strategy=multi-reward RL fine-tuning2026.060.26922.520.355
GRPO-GuardBase Model=FLUX2-klein-base-9B, Strategy=multi-reward RL fine-tuning2026.060.26921.990.349
Flow-CPSBase Model=SD3.5-medium, Training Strategy=multi-reward RL fine-tuning2026.060.26522.080.343
GRPO-GuardBase Model=SD3.5-medium, Strategy=single-reward RL fine-tuning2026.060.26519.940.214
Flow-DPPOBase Model=SD3.5-medium, Strategy=single-reward RL fine-tuning2026.060.26520.450.253
Flow-CPSBase Model=SD3.5-medium, Strategy=multi-reward RL fine-tuning2026.060.26522.080.343
Flow-DPPO + CPSBase Model=FLUX2-klein-base-9B, Strategy=single-reward RL fine-tuning2026.060.26520.790.272
Flow-GRPOBase Model=FLUX2-klein-base-9B, Strategy=single-reward RL fine-tuning2026.060.26420.840.28
Diffusion-NFTBase Model=SD3.5-medium, Strategy=single-reward RL fine-tuning2026.060.26220.240.239
Flow-CPSBase Model=SD3.5-medium, Strategy=single-reward RL fine-tuning2026.060.2619.940.22
FLUX2-klein-base-9BBase Model=FLUX2-klein-base-9B, Training Strategy=Pretrained baselines (before RL)2026.060.25420.050.23
FLUX2-klein-base-9BBase Model=FLUX2-klein-base-9B, Strategy=Pretrained (before RL)2026.060.25420.050.23
Flow-GRPOBase Model=SD3.5-medium, Strategy=single-reward RL fine-tuning2026.060.25219.330.206
SD3.5-mediumBase Model=SD3.5-medium, Training Strategy=Pretrained baselines (before RL)2026.060.24419.990.21
SD3.5-mediumBase Model=SD3.5-medium, Strategy=Pretrained (before RL)2026.060.24419.990.21
GRPO-GuardBase Model=FLUX2-klein-base-9B, Strategy=single-reward RL fine-tuning2026.060.2318.450.167