Training Diffusion Models with Reinforcement Learning — mentioned by kikijiji

Fri, 11 Aug 2023 05:25:23 GMT

Congrats on the launch. It's an interesting idea. What are your thoughts on DPPO[1] and if your model(s) could be integrated into that or a similar process to fine tune the original model? Could that potentially remove the need for this product? [1] https://arxiv.org/abs/2305.13301

Paper and discussion history. A mention is not an endorsement.

Training Diffusion Models with Reinforcement Learning · HackerPapers discussions

Training Diffusion Models with Reinforcement Learning — mentioned by kikijiji