This is the selected Image RM checkpoint trained on liuhuohuo2/pick-a-pic-v2, using stabilityai/stable-diffusion-3.5-medium as the backbone.

eval was used as the primary selection metric and eval_unique as the complementary metric. This run provided the best overall balance among the completed T5-256 RM runs, with only mild late drift in eval loss and no late rise in eval_unique loss.

Use this checkpoint for reward labeling and reward-based alignment.