You can fine-tune Stable Diffusion on a reward function via reinforcement learning with the 馃 TRL library and 馃 Diffusers. This is done with the Denoising Diffusion Policy Optimization (DDPO) algorithm introduced by Black et al. in Training Diffusion Models with Reinforcement Learning, which is implemented in 馃 TRL with the [~trl.DDPOTrainer].
For more information, check out the [~trl.DDPOTrainer] API reference and the Finetune Stable Diffusion Models with DDPO via TRL blog post.