Ben Glickenhaus

Excited to see this is WIP! I was just going down the rabbit hole if implementing some of this myself. > The code specific to RL was only used during...

I think my implementation of value guided planning [here](https://github.com/bglick13/diffusers/tree/rl) is ready for a look. Tested on hopper and it looks good.

@lukovnikov sorry for the delayed response. I think that's an important meta decision to make with the Diffusers team! I've seen a similar approach e.g., in the Imagic PR. For...

> update the config for the RL models on the hub to get the mid_layer functionality in. @bglick13 is this easy? Done!

I recently developed a community pipeline and found it a bit awkward to develop and test before it gets pulled into main. I think the issue is with how `from_pretrained`...

Wow that's awesome - thanks for being so quick on that!

DDIM will hopefully be ready for review soon too. Results training on it are still a little pixelated, but you can clearly see the shape of a butterfly. I'm guessing...

Hi, thank you for the response. I am using essentially the example from the read me, but with my own game. I figured out if I lower the learning rate...