You are viewing v0.24.0 version.
A newer version
v0.31.0 is available.
Reinforcement learning training with DDPO
You can fine-tune Stable Diffusion on a reward function via reinforcement learning with the 🤗 TRL library and 🤗 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 🤗 TRL with the DDPOTrainer.
For more information, check out the DDPOTrainer API reference and the Finetune Stable Diffusion Models with DDPO via TRL blog post.