Training Diffusion Models with Reinforcement Learning

Open paper
Benchmark Model Rank Results
text-to-image-generation-on-drawbenchLCM (DDPO)#3Aesthetics (Laion Aesthtetics Predictor): 6.0121…
text-to-image-generation-on-drawbenchStable Diffusion 1.5 (DDPO)#6Aesthetics (Laion Aesthtetics Predictor): 5.6748…

Rank counts only results with a code link.